Publications
Search
121.
ZarrieB, Sina; Hough, Julian; Kennington, Casey; Manuvinakurike, Ramesh; DeVault, David; Fernández, Raquel; Schlangen, David
PentoRef: A Corpus of Spoken References in Task-oriented Dialogues Proceedings Article
In: 10th edition of the Language Resources and Evaluation Conference, ELRA, Portorož, Slovenia, 2016.
@inproceedings{zarrieb_pentoref_2016,
title = {PentoRef: A Corpus of Spoken References in Task-oriented Dialogues},
author = {Sina ZarrieB and Julian Hough and Casey Kennington and Ramesh Manuvinakurike and David DeVault and Raquel Fernández and David Schlangen},
url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/563_Paper.pdf},
year = {2016},
date = {2016-05-01},
booktitle = {10th edition of the Language Resources and Evaluation Conference},
publisher = {ELRA},
address = {Portorož, Slovenia},
abstract = {PentoRef is a corpus of task-oriented dialogues collected in systematically manipulated settings. The corpus is multilingual, with English and German sections, and overall comprises more than 20000 utterances. The dialogues are fully transcribed and annotated with referring expressions mapped to objects in corresponding visual scenes, which makes the corpus a rich resource for research on spoken referring expressions in generation and resolution. The corpus includes several sub-corpora that correspond to different dialogue situations where parameters related to interactivity, visual access, and verbal channel have been manipulated in systematic ways. The corpus thus lends itself to very targeted studies of reference in spontaneous dialogue.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
PentoRef is a corpus of task-oriented dialogues collected in systematically manipulated settings. The corpus is multilingual, with English and German sections, and overall comprises more than 20000 utterances. The dialogues are fully transcribed and annotated with referring expressions mapped to objects in corresponding visual scenes, which makes the corpus a rich resource for research on spoken referring expressions in generation and resolution. The corpus includes several sub-corpora that correspond to different dialogue situations where parameters related to interactivity, visual access, and verbal channel have been manipulated in systematic ways. The corpus thus lends itself to very targeted studies of reference in spontaneous dialogue.
122.
Konovalov, Vasily; Artstein, Ron; Melamud, Oren; Dagan, Ido
The Negochat Corpus of Human-agent Negotiation Dialogues Proceedings Article
In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 3141–3145, European Language Resources Association (ELRA), Portorož, Slovenia, 2016.
@inproceedings{konovalov_negochat_2016,
title = {The Negochat Corpus of Human-agent Negotiation Dialogues},
author = {Vasily Konovalov and Ron Artstein and Oren Melamud and Ido Dagan},
url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/240_Paper.pdf},
year = {2016},
date = {2016-05-01},
booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
pages = {3141–3145},
publisher = {European Language Resources Association (ELRA)},
address = {Portorož, Slovenia},
abstract = {Annotated in-domain corpora are crucial to the successful development of dialogue systems of automated agents, and in particular for developing natural language understanding (NLU) components of such systems. Unfortunately, such important resources are scarce. In this work, we introduce an annotated natural language human-agent dialogue corpus in the negotiation domain. The corpus was collected using Amazon Mechanical Turk following the ‘Wizard-Of-Oz’ approach, where a ‘wizard’ human translates the participants’ natural language utterances in real time into a semantic language. Once dialogue collection was completed, utterances were annotated with intent labels by two independent annotators, achieving high inter-annotator agreement. Our initial experiments with an SVM classifier show that automatically inferring such labels from the utterances is far from trivial. We make our corpus publicly available to serve as an aid in the development of dialogue systems for negotiation agents, and suggest that analogous corpora can be created following our methodology and using our available source code. To the best of our knowledge this is the first publicly available negotiation dialogue corpus.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Annotated in-domain corpora are crucial to the successful development of dialogue systems of automated agents, and in particular for developing natural language understanding (NLU) components of such systems. Unfortunately, such important resources are scarce. In this work, we introduce an annotated natural language human-agent dialogue corpus in the negotiation domain. The corpus was collected using Amazon Mechanical Turk following the ‘Wizard-Of-Oz’ approach, where a ‘wizard’ human translates the participants’ natural language utterances in real time into a semantic language. Once dialogue collection was completed, utterances were annotated with intent labels by two independent annotators, achieving high inter-annotator agreement. Our initial experiments with an SVM classifier show that automatically inferring such labels from the utterances is far from trivial. We make our corpus publicly available to serve as an aid in the development of dialogue systems for negotiation agents, and suggest that analogous corpora can be created following our methodology and using our available source code. To the best of our knowledge this is the first publicly available negotiation dialogue corpus.
123.
Gilani, Setareh Nasihati; Sheetz, Kraig; Lucas, Gale; Traum, David
What Kind of Stories Should a Virtual Human Swap? Proceedings Article
In: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, pp. 1437–1438, International Foundation for Autonomous Agents and Multiagent Systems, Singapore, 2016, ISBN: 978-1-4503-4239-1.
@inproceedings{nasihati_gilani_what_2016,
title = {What Kind of Stories Should a Virtual Human Swap?},
author = {Setareh Nasihati Gilani and Kraig Sheetz and Gale Lucas and David Traum},
url = {http://dl.acm.org/citation.cfm?id=2937198},
isbn = {978-1-4503-4239-1},
year = {2016},
date = {2016-05-01},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems},
pages = {1437–1438},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Singapore},
abstract = {Stories are pervasive in conversation between people [5]. They are used to establish identity pass on cultural heritage, and build rapport. Often stories are swapped when one conversational participant will reply to a story with a story. Stories are also told by virtual humans [1, 6, 2]. In creating or mining stories for a virtual human (VH) to tell, there are a number of considerations that come up about what kinds of stories should be told, and how the stories should be related to the virtual human's identity, such as whether the identity should be human or arti⬚cial, and whether the stories should be about the virtual human or about someone else. We designed a set of virtual human characters who can engage in a simple form of story-swapping. Each of the characters can engage in simple interactions such as greetings and closings and can respond to a set of textbackslashtextbackslashtextbackslashtextbackslashice-breaker" questions, that might be used on a ⬚rst date or similar textbackslashtextbackslashtextbackslashtextbackslashget to know you" encounter. For these questions the character's answer includes a story. We created 4 character response sets, to have all combinations of identity (human or arti⬚cial) and perspective (⬚rst person stories about the narrator, or third person stories about someone else). We also designed an experiment to try to explore the collective impact of above principles on people who interact with the characters. Participants interact with two of the above characters in a "get to know you" scenario. We investigate the degree of reciprocity where people respond to the character with their own stories, and also compare rapport of participants with the characters as well as the impressions of the character's personality.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stories are pervasive in conversation between people [5]. They are used to establish identity pass on cultural heritage, and build rapport. Often stories are swapped when one conversational participant will reply to a story with a story. Stories are also told by virtual humans [1, 6, 2]. In creating or mining stories for a virtual human (VH) to tell, there are a number of considerations that come up about what kinds of stories should be told, and how the stories should be related to the virtual human's identity, such as whether the identity should be human or arti⬚cial, and whether the stories should be about the virtual human or about someone else. We designed a set of virtual human characters who can engage in a simple form of story-swapping. Each of the characters can engage in simple interactions such as greetings and closings and can respond to a set of textbackslashtextbackslashtextbackslashtextbackslashice-breaker" questions, that might be used on a ⬚rst date or similar textbackslashtextbackslashtextbackslashtextbackslashget to know you" encounter. For these questions the character's answer includes a story. We created 4 character response sets, to have all combinations of identity (human or arti⬚cial) and perspective (⬚rst person stories about the narrator, or third person stories about someone else). We also designed an experiment to try to explore the collective impact of above principles on people who interact with the characters. Participants interact with two of the above characters in a "get to know you" scenario. We investigate the degree of reciprocity where people respond to the character with their own stories, and also compare rapport of participants with the characters as well as the impressions of the character's personality.
124.
Pincus, Eli; Traum, David
Towards Automatic Identification of Effective Clues for Team Word-Guessing Games Proceedings Article
In: Proceedings of the Language Resources and Evaluation Conference (LREC), pp. 2741–2747, European Language Resources Association, Portorož, Slovenia, 2016.
@inproceedings{pincus_towards_2016,
title = {Towards Automatic Identification of Effective Clues for Team Word-Guessing Games},
author = {Eli Pincus and David Traum},
url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/762_Paper.pdf},
year = {2016},
date = {2016-05-01},
booktitle = {Proceedings of the Language Resources and Evaluation Conference (LREC)},
pages = {2741–2747},
publisher = {European Language Resources Association},
address = {Portorož, Slovenia},
abstract = {Team word-guessing games where one player, the clue-giver, gives clues attempting to elicit a target-word from another player, the receiver, are a popular form of entertainment and also used for educational purposes. Creating an engaging computational agent capable of emulating a talented human clue-giver in a timed word-guessing game depends on the ability to provide effective clues (clues able to elicit a correct guess from a human receiver). There are many available web resources and databases that can be mined for the raw material for clues for target-words; however, a large number of those clues are unlikely to be able to elicit a correct guess from a human guesser. In this paper, we propose a method for automatically filtering a clue corpus for effective clues for an arbitrary target-word from a larger set of potential clues, using machine learning on a set of features of the clues, including point-wise mutual information between a clue’s constituent words and a clue’s target-word. The results of the experiments significantly improve the average clue quality over previous approaches, and bring quality rates in-line with measures of human clue quality derived from a corpus of human-human interactions. The paper also introduces the data used to develop this method; audio recordings of people making guesses after having heard the clues being spoken by a synthesized voice (Pincus and Traum, 2016).},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Team word-guessing games where one player, the clue-giver, gives clues attempting to elicit a target-word from another player, the receiver, are a popular form of entertainment and also used for educational purposes. Creating an engaging computational agent capable of emulating a talented human clue-giver in a timed word-guessing game depends on the ability to provide effective clues (clues able to elicit a correct guess from a human receiver). There are many available web resources and databases that can be mined for the raw material for clues for target-words; however, a large number of those clues are unlikely to be able to elicit a correct guess from a human guesser. In this paper, we propose a method for automatically filtering a clue corpus for effective clues for an arbitrary target-word from a larger set of potential clues, using machine learning on a set of features of the clues, including point-wise mutual information between a clue’s constituent words and a clue’s target-word. The results of the experiments significantly improve the average clue quality over previous approaches, and bring quality rates in-line with measures of human clue quality derived from a corpus of human-human interactions. The paper also introduces the data used to develop this method; audio recordings of people making guesses after having heard the clues being spoken by a synthesized voice (Pincus and Traum, 2016).
125.
Collins, Kathryn J.; Traum, David
Towards A Multi-Dimensional Taxonomy Of Stories In Dialogue Proceedings Article
In: Proceedings of the Language Resources and Evaluation Conference (LREC), pp. 118–124, European Language Resources Association, Portorož, Slovenia, 2016, ISBN: 978-2-9517408-9-1.
@inproceedings{collins_towards_2016,
title = {Towards A Multi-Dimensional Taxonomy Of Stories In Dialogue},
author = {Kathryn J. Collins and David Traum},
url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/354_Paper.pdf},
isbn = {978-2-9517408-9-1},
year = {2016},
date = {2016-05-01},
booktitle = {Proceedings of the Language Resources and Evaluation Conference (LREC)},
pages = {118–124},
publisher = {European Language Resources Association},
address = {Portorož, Slovenia},
abstract = {In this paper, we present a taxonomy of stories told in dialogue. We based our scheme on prior work analyzing narrative structure and method of telling, relation to storyteller identity, as well as some categories particular to dialogue, such as how the story gets introduced. Our taxonomy currently has 5 major dimensions, with most having sub-dimensions - each dimension has an associated set of dimension-specific labels. We adapted an annotation tool for this taxonomy and have annotated portions of two different dialogue corpora, Switchboard and the Distress Analysis Interview Corpus. We present examples of some of the tags and concepts with stories from Switchboard, and some initial statistics of frequencies of the tags.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a taxonomy of stories told in dialogue. We based our scheme on prior work analyzing narrative structure and method of telling, relation to storyteller identity, as well as some categories particular to dialogue, such as how the story gets introduced. Our taxonomy currently has 5 major dimensions, with most having sub-dimensions - each dimension has an associated set of dimension-specific labels. We adapted an annotation tool for this taxonomy and have annotated portions of two different dialogue corpora, Switchboard and the Distress Analysis Interview Corpus. We present examples of some of the tags and concepts with stories from Switchboard, and some initial statistics of frequencies of the tags.
126.
Gandhe, Sudeep; Traum, David
A Semi-automated Evaluation Metric for Dialogue Model Coherence Book Section
In: Situated Dialog in Speech-Based Human-Computer Interaction, pp. 217–225, Springer International Publishing, Cham, 2016, ISBN: 978-3-319-21833-5 978-3-319-21834-2.
@incollection{gandhe_semi-automated_2016,
title = {A Semi-automated Evaluation Metric for Dialogue Model Coherence},
author = {Sudeep Gandhe and David Traum},
url = {http://link.springer.com/10.1007/978-3-319-21834-2_19},
isbn = {978-3-319-21833-5 978-3-319-21834-2},
year = {2016},
date = {2016-04-01},
booktitle = {Situated Dialog in Speech-Based Human-Computer Interaction},
pages = {217–225},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {We propose a new metric, Voted Appropriateness, which can be used to automatically evaluate dialogue policy decisions, once some wizard data has been collected. We show that this metric outperforms a previously proposed metric Weak agreement.We also present a taxonomy for dialogue model evaluation schemas, and orient our new metric within this taxonomy.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
We propose a new metric, Voted Appropriateness, which can be used to automatically evaluate dialogue policy decisions, once some wizard data has been collected. We show that this metric outperforms a previously proposed metric Weak agreement.We also present a taxonomy for dialogue model evaluation schemas, and orient our new metric within this taxonomy.
127.
Artstein, Ron; Silver, Kenneth
Ethics for a Combined Human-Machine Dialogue Agent Proceedings Article
In: Ethical and Moral Considerations in Non-Human Agents: Papers from the AAAI Spring Symposium, pp. 184–189, AAAI Press, Stanford, California, 2016.
@inproceedings{artstein_ethics_2016,
title = {Ethics for a Combined Human-Machine Dialogue Agent},
author = {Ron Artstein and Kenneth Silver},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS16/paper/viewFile/12706/11948},
year = {2016},
date = {2016-03-01},
booktitle = {Ethical and Moral Considerations in Non-Human Agents: Papers from the AAAI Spring Symposium},
pages = {184–189},
publisher = {AAAI Press},
address = {Stanford, California},
abstract = {We discuss philosophical and ethical issues that arise from a dialogue system intended to portray a real person, using recordings of the person together with a machine agent that selects recordings during a synchronous conversation with a user. System output may count as actions of the speaker if the speaker intends to communicate with users and the outputs represent what the speaker would have chosen to say in context; in such cases the system can justifiably be said to be holding a conversation that is offset in time. The autonomous agent may at times misrepresent the speaker’s intentions, and such failures are analogous to good-faith misunderstandings. The user may or may not need to be informed that the speaker is not organically present, depending on the application.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We discuss philosophical and ethical issues that arise from a dialogue system intended to portray a real person, using recordings of the person together with a machine agent that selects recordings during a synchronous conversation with a user. System output may count as actions of the speaker if the speaker intends to communicate with users and the outputs represent what the speaker would have chosen to say in context; in such cases the system can justifiably be said to be holding a conversation that is offset in time. The autonomous agent may at times misrepresent the speaker’s intentions, and such failures are analogous to good-faith misunderstandings. The user may or may not need to be informed that the speaker is not organically present, depending on the application.
128.
Georgila, Kallirroi; Pynadath, David V.
Towards a Computational Model of Human Opinion Dynamics in Response to Real-World Events Proceedings Article
In: Proceedings of The 29th International FLAIRS Conference, pp. 44–49, AAAI Press, Key Largo, FL, 2016.
@inproceedings{georgila_towards_2016,
title = {Towards a Computational Model of Human Opinion Dynamics in Response to Real-World Events},
author = {Kallirroi Georgila and David V. Pynadath},
url = {http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS16/paper/view/12960/12539},
year = {2016},
date = {2016-03-01},
booktitle = {Proceedings of The 29th International FLAIRS Conference},
pages = {44–49},
publisher = {AAAI Press},
address = {Key Largo, FL},
abstract = {Accurate multiagent social simulation requires a computational model of how people incorporate their observations of real-world events into their beliefs about the state of their world. Current methods for creating such agent-based models typically rely on manual input that can be both burdensome and subjective. In this investigation, we instead pursue automated methods that can translate available data into the desired computational models. For this purpose, we use a corpus of real-world events in combination with longitudinal public opinion polls on a variety of opinion issues. We perform two experiments using automated methods taken from the literature. In our first experiment, we train maximum entropy classifiers to model changes in opinion scores as a function of real-world events. We measure and analyze the accuracy of our learned classifiers by comparing the opinion scores they generate against the opinion scores occurring in a held-out subset of our corpus. In our second experiment, we learn Bayesian networks to capture the same function.We then compare the dependency structures induced by the two methods to identify the event features that have the most significant effect on changes in public opinion.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Accurate multiagent social simulation requires a computational model of how people incorporate their observations of real-world events into their beliefs about the state of their world. Current methods for creating such agent-based models typically rely on manual input that can be both burdensome and subjective. In this investigation, we instead pursue automated methods that can translate available data into the desired computational models. For this purpose, we use a corpus of real-world events in combination with longitudinal public opinion polls on a variety of opinion issues. We perform two experiments using automated methods taken from the literature. In our first experiment, we train maximum entropy classifiers to model changes in opinion scores as a function of real-world events. We measure and analyze the accuracy of our learned classifiers by comparing the opinion scores they generate against the opinion scores occurring in a held-out subset of our corpus. In our second experiment, we learn Bayesian networks to capture the same function.We then compare the dependency structures induced by the two methods to identify the event features that have the most significant effect on changes in public opinion.
129.
Kaplan, Jonas T.; Gimbel, Sarah I.; Dehghani, Morteza; Immordino-Yang, Mary Helen; Sagae, Kenji; Wong, Jennifer D.; Tipper, Christine M.; Damasio, Hanna; Gordon, Andrew S.; Damasio, Antonio
Processing Narratives Concerning Protected Values: A Cross-Cultural Investigation of Neural Correlates Journal Article
In: Cerebral Cortex, 2016, ISSN: 1047-3211, 1460-2199.
@article{kaplan_processing_2016,
title = {Processing Narratives Concerning Protected Values: A Cross-Cultural Investigation of Neural Correlates},
author = {Jonas T. Kaplan and Sarah I. Gimbel and Morteza Dehghani and Mary Helen Immordino-Yang and Kenji Sagae and Jennifer D. Wong and Christine M. Tipper and Hanna Damasio and Andrew S. Gordon and Antonio Damasio},
url = {http://www.cercor.oxfordjournals.org/lookup/doi/10.1093/cercor/bhv325},
doi = {10.1093/cercor/bhv325},
issn = {1047-3211, 1460-2199},
year = {2016},
date = {2016-01-01},
journal = {Cerebral Cortex},
abstract = {Narratives are an important component of culture and play a central role in transmitting social values. Little is known, however, about how the brain of a listener/reader processes narratives. A receiver's response to narration is influenced by the narrator's framing and appeal to values. Narratives that appeal to “protected values,” including core personal, national, or religious values, may be particularly effective at influencing receivers. Protected values resist compromise and are tied with identity, affective value, moral decision-making, and other aspects of social cognition. Here, we investigated the neural mechanisms underlying reactions to protected values in narratives. During fMRI scanning, we presented 78 American, Chinese, and Iranian participants with real-life stories distilled from a corpus of over 20 million weblogs. Reading these stories engaged the posterior medial, medial prefrontal, and temporo-parietal cortices. When participants believed that the protagonist was appealing to a protected value, signal in these regions was increased compared with when no protected value was perceived, possibly reflecting the intensive and iterative search required to process this material. The effect strength also varied across groups, potentially reflecting cultural differences in the degree of concern for protected values.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Narratives are an important component of culture and play a central role in transmitting social values. Little is known, however, about how the brain of a listener/reader processes narratives. A receiver's response to narration is influenced by the narrator's framing and appeal to values. Narratives that appeal to “protected values,” including core personal, national, or religious values, may be particularly effective at influencing receivers. Protected values resist compromise and are tied with identity, affective value, moral decision-making, and other aspects of social cognition. Here, we investigated the neural mechanisms underlying reactions to protected values in narratives. During fMRI scanning, we presented 78 American, Chinese, and Iranian participants with real-life stories distilled from a corpus of over 20 million weblogs. Reading these stories engaged the posterior medial, medial prefrontal, and temporo-parietal cortices. When participants believed that the protagonist was appealing to a protected value, signal in these regions was increased compared with when no protected value was perceived, possibly reflecting the intensive and iterative search required to process this material. The effect strength also varied across groups, potentially reflecting cultural differences in the degree of concern for protected values.
130.
Traum, David; Jones, Andrew; Hays, Kia; Maio, Heather; Alexander, Oleg; Artstein, Ron; Debevec, Paul; Gainer, Alesia; Georgila, Kallirroi; Haase, Kathleen; Jungblut, Karen; Leuski, Anton; Smith, Stephen; Swartout, William
New Dimensions in Testimony: Digitally Preserving a Holocaust Survivor’s Interactive Storytelling Book Section
In: Interactive Storytelling, vol. 9445, pp. 269–281, Springer International Publishing, Copenhagen, Denmark, 2015, ISBN: 978-3-319-27035-7 978-3-319-27036-4.
@incollection{traum_new_2015,
title = {New Dimensions in Testimony: Digitally Preserving a Holocaust Survivor’s Interactive Storytelling},
author = {David Traum and Andrew Jones and Kia Hays and Heather Maio and Oleg Alexander and Ron Artstein and Paul Debevec and Alesia Gainer and Kallirroi Georgila and Kathleen Haase and Karen Jungblut and Anton Leuski and Stephen Smith and William Swartout},
url = {http://link.springer.com/10.1007/978-3-319-27036-4_26},
isbn = {978-3-319-27035-7 978-3-319-27036-4},
year = {2015},
date = {2015-12-01},
booktitle = {Interactive Storytelling},
volume = {9445},
pages = {269–281},
publisher = {Springer International Publishing},
address = {Copenhagen, Denmark},
abstract = {We describe a digital system that allows people to have an interactive conversation with a human storyteller (a Holocaust survivor) who has recorded a number of dialogue contributions, including many compelling narratives of his experiences and thoughts. The goal is to preserve as much as possible of the experience of face-to-face interaction. The survivor's stories, answers to common questions, and testimony are recorded in high ⬚delity, and then delivered interactively to an audience as responses to spoken questions. People can ask questions and receive answers on a broad range of topics including the survivor's experiences before, after and during the war, his attitudes and philosophy. Evaluation results show that most user questions can be addressed by the system, and that audiences are highly engaged with the resulting interaction.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
We describe a digital system that allows people to have an interactive conversation with a human storyteller (a Holocaust survivor) who has recorded a number of dialogue contributions, including many compelling narratives of his experiences and thoughts. The goal is to preserve as much as possible of the experience of face-to-face interaction. The survivor's stories, answers to common questions, and testimony are recorded in high ⬚delity, and then delivered interactively to an audience as responses to spoken questions. People can ask questions and receive answers on a broad range of topics including the survivor's experiences before, after and during the war, his attitudes and philosophy. Evaluation results show that most user questions can be addressed by the system, and that audiences are highly engaged with the resulting interaction.
131.
Chatterjee, Moitreya; Leuski, Anton
A Novel Statistical Approach for Image and Video Retrieval and Its Adaption for Active Learning Book Section
In: A Novel Statistical Approach for Image and Video Retrieval and Its Adaption for Active Learning, pp. 935–938, ACM, Brisbane, Australia, 2015, ISBN: 978-1-4503-3459-4.
@incollection{chatterjee_novel_2015,
title = {A Novel Statistical Approach for Image and Video Retrieval and Its Adaption for Active Learning},
author = {Moitreya Chatterjee and Anton Leuski},
url = {http://dl.acm.org/citation.cfm?id=2806368},
isbn = {978-1-4503-3459-4},
year = {2015},
date = {2015-10-01},
booktitle = {A Novel Statistical Approach for Image and Video Retrieval and Its Adaption for Active Learning},
pages = {935–938},
publisher = {ACM},
address = {Brisbane, Australia},
abstract = {The ever expanding multimedia content (such as images and videos), especially on the web, necessitates e⬚ective text query-based search (or retrieval) systems. Popular approaches for addressing this issue, use the query-likelihood model which fails to capture the user's information needs. In this work therefore, we explore a new ranking approach in the context of image and video retrieval from text queries. Our approach assumes two separate underlying distributions for query and the document respectively. We then, determine the extent of similarity between these two statistical distributions for the task of ranking. Furthermore we extend our approach, using Active Learning techniques, to address the question of obtaining a good performance without requiring a fully labeled training dataset. This is done by taking Sample Uncertainty, Density and Diversity into account. Our experiments on the popular TRECVID corpus and the open, relatively small-sized USC SmartBody corpus show that we are almost at-par or sometimes better than multiple state-of-the-art baselines.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The ever expanding multimedia content (such as images and videos), especially on the web, necessitates e⬚ective text query-based search (or retrieval) systems. Popular approaches for addressing this issue, use the query-likelihood model which fails to capture the user's information needs. In this work therefore, we explore a new ranking approach in the context of image and video retrieval from text queries. Our approach assumes two separate underlying distributions for query and the document respectively. We then, determine the extent of similarity between these two statistical distributions for the task of ranking. Furthermore we extend our approach, using Active Learning techniques, to address the question of obtaining a good performance without requiring a fully labeled training dataset. This is done by taking Sample Uncertainty, Density and Diversity into account. Our experiments on the popular TRECVID corpus and the open, relatively small-sized USC SmartBody corpus show that we are almost at-par or sometimes better than multiple state-of-the-art baselines.
132.
Kang, Sin-Hwa; Feng, Andrew W.; Leuski, Anton; Casas, Dan; Shapiro, Ari
The Effect of An Animated Virtual Character on Mobile Chat Interactions Book Section
In: Proceedings of the 3rd International Conference on Human-Agent Interaction, pp. 105–112, ACM, Daegu, Korea, 2015, ISBN: 978-1-4503-3527-0.
@incollection{kang_effect_2015,
title = {The Effect of An Animated Virtual Character on Mobile Chat Interactions},
author = {Sin-Hwa Kang and Andrew W. Feng and Anton Leuski and Dan Casas and Ari Shapiro},
url = {http://dl.acm.org/citation.cfm?id=2814957},
isbn = {978-1-4503-3527-0},
year = {2015},
date = {2015-10-01},
booktitle = {Proceedings of the 3rd International Conference on Human-Agent Interaction},
pages = {105–112},
publisher = {ACM},
address = {Daegu, Korea},
abstract = {This study explores presentation techniques for a 3D animated chat-based virtual human that communicates engagingly with users. Interactions with the virtual human occur via a smartphone outside of the lab in natural settings. Our work compares the responses of users who interact with no image or a static image of a virtual character as opposed to the animated visage of a virtual human capable of displaying appropriate nonverbal behavior. We further investigate users’ responses to the animated character’s gaze aversion which displayed the character’s act of looking away from users and was presented as a listening behavior. The findings of our study demonstrate that people tend to engage in conversation more by talking for a longer amount of time when they interact with a 3D animated virtual human that averts its gaze, compared to an animated virtual human that does not avert its gaze, a static image of a virtual character, or an audio-only interface.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
This study explores presentation techniques for a 3D animated chat-based virtual human that communicates engagingly with users. Interactions with the virtual human occur via a smartphone outside of the lab in natural settings. Our work compares the responses of users who interact with no image or a static image of a virtual character as opposed to the animated visage of a virtual human capable of displaying appropriate nonverbal behavior. We further investigate users’ responses to the animated character’s gaze aversion which displayed the character’s act of looking away from users and was presented as a listening behavior. The findings of our study demonstrate that people tend to engage in conversation more by talking for a longer amount of time when they interact with a 3D animated virtual human that averts its gaze, compared to an animated virtual human that does not avert its gaze, a static image of a virtual character, or an audio-only interface.
133.
Papangelis, Alexandros; Georgila, Kallirroi
Reinforcement learning of multi-issue negotiation dialogue policies Proceedings Article
In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 154–158, Association for Computational Linguistics, Prague, Czech Republic, 2015.
@inproceedings{papangelis_reinforcement_2015,
title = {Reinforcement learning of multi-issue negotiation dialogue policies},
author = {Alexandros Papangelis and Kallirroi Georgila},
url = {http://www.aclweb.org/anthology/W15-4621},
year = {2015},
date = {2015-09-01},
booktitle = {Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
pages = {154–158},
publisher = {Association for Computational Linguistics},
address = {Prague, Czech Republic},
abstract = {We use reinforcement learning (RL) to learn a multi-issue negotiation dialogue policy. For training and evaluation, we build a hand-crafted agenda-based policy, which serves as the negotiation partner of the RL policy. Both the agendabased and the RL policies are designed to work for a large variety of negotiation settings, and perform well against negotiation partners whose behavior has not been observed before. We evaluate the two models by having them negotiate against each other under various settings. The learned model consistently outperforms the agenda-based model. We also ask human raters to rate negotiation transcripts between the RL policy and the agenda-based policy, regarding the rationality of the two negotiators. The RL policy is perceived as more rational than the agenda-based policy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We use reinforcement learning (RL) to learn a multi-issue negotiation dialogue policy. For training and evaluation, we build a hand-crafted agenda-based policy, which serves as the negotiation partner of the RL policy. Both the agendabased and the RL policies are designed to work for a large variety of negotiation settings, and perform well against negotiation partners whose behavior has not been observed before. We evaluate the two models by having them negotiate against each other under various settings. The learned model consistently outperforms the agenda-based model. We also ask human raters to rate negotiation transcripts between the RL policy and the agenda-based policy, regarding the rationality of the two negotiators. The RL policy is perceived as more rational than the agenda-based policy.
134.
Traum, David; Georgila, Kallirroi; Artstein, Ron; Leuski, Anton
Evaluating Spoken Dialogue Processing for Time-Offset Interaction Proceedings Article
In: Proceedings of 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL), pp. 199–208, Association for Computational Linguistics, Prague, Czech Republic, 2015, ISBN: 978-1-941643-75-4.
@inproceedings{traum_evaluating_2015,
title = {Evaluating Spoken Dialogue Processing for Time-Offset Interaction},
author = {David Traum and Kallirroi Georgila and Ron Artstein and Anton Leuski},
url = {http://ict.usc.edu/pubs/Evaluating%20Spoken%20Dialogue%20Processing%20for%20Time-Offset%20Interaction.pdf},
isbn = {978-1-941643-75-4},
year = {2015},
date = {2015-09-01},
booktitle = {Proceedings of 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)},
pages = {199–208},
publisher = {Association for Computational Linguistics},
address = {Prague, Czech Republic},
abstract = {This paper presents the first evaluation of a full automated prototype system for time-offset interaction, that is, conversation between a live person and recordings of someone who is not temporally co-present. Speech recognition reaches word error rates as low as 5% with general purpose language models and 19% with domain-specific models, and language understanding can identify appropriate direct responses to 60–66% of user utterances while keeping errors to 10–16% (the remainder being indirect, or off-topic responses). This is sufficient to enable a natural flow and relatively open-ended conversations, with a collection of under 2000 recorded statements.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents the first evaluation of a full automated prototype system for time-offset interaction, that is, conversation between a live person and recordings of someone who is not temporally co-present. Speech recognition reaches word error rates as low as 5% with general purpose language models and 19% with domain-specific models, and language understanding can identify appropriate direct responses to 60–66% of user utterances while keeping errors to 10–16% (the remainder being indirect, or off-topic responses). This is sufficient to enable a natural flow and relatively open-ended conversations, with a collection of under 2000 recorded statements.
135.
Paetzel, Maike; Manuvinakurike, Ramesh; DeVault, David
"So, which one is it?" The effect of alternative incremental architectures in a high-performance game-playing agent Proceedings Article
In: Proceedings of SIGDIAL 2015, pp. 77 – 86, Prague, Czech Republic, 2015.
@inproceedings{paetzel_so_2015,
title = {"So, which one is it?" The effect of alternative incremental architectures in a high-performance game-playing agent},
author = {Maike Paetzel and Ramesh Manuvinakurike and David DeVault},
url = {http://ict.usc.edu/pubs/So,%20which%20one%20is%20it%20-%20The%20effect%20of%20alternative%20incremental%20architectures%20in%20a%20high-performance%20game-playing%20agent.pdf},
year = {2015},
date = {2015-09-01},
booktitle = {Proceedings of SIGDIAL 2015},
pages = {77 – 86},
address = {Prague, Czech Republic},
abstract = {This paper introduces Eve, a highperformance agent that plays a fast-paced image matching game in a spoken dialogue with a human partner. The agent can be optimized and operated in three different modes of incremental speech processing that optionally include incremental speech recognition, language understanding, and dialogue policies. We present our framework for training and evaluating the agent’s dialogue policies. In a user study involving 125 human participants, we evaluate three incremental architectures against each other and also compare their performance to human-human gameplay. Our study reveals that the most fully incremental agent achieves game scores that are comparable to those achieved in human-human gameplay, are higher than those achieved by partially and nonincremental versions, and are accompanied by improved user perceptions of efficiency, understanding of speech, and naturalness of interaction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper introduces Eve, a highperformance agent that plays a fast-paced image matching game in a spoken dialogue with a human partner. The agent can be optimized and operated in three different modes of incremental speech processing that optionally include incremental speech recognition, language understanding, and dialogue policies. We present our framework for training and evaluating the agent’s dialogue policies. In a user study involving 125 human participants, we evaluate three incremental architectures against each other and also compare their performance to human-human gameplay. Our study reveals that the most fully incremental agent achieves game scores that are comparable to those achieved in human-human gameplay, are higher than those achieved by partially and nonincremental versions, and are accompanied by improved user perceptions of efficiency, understanding of speech, and naturalness of interaction.
136.
Pincus, Eli; Georgila, Kallirroi; Traum, David
Which Synthetic Voice Should I Choose for an Evocative Task? Proceedings Article
In: Proceeding of SIGDIAL 2015, pp. 105 – 113, Prague, Czech Republic, 2015.
@inproceedings{pincus_which_2015,
title = {Which Synthetic Voice Should I Choose for an Evocative Task?},
author = {Eli Pincus and Kallirroi Georgila and David Traum},
url = {http://ict.usc.edu/pubs/Which%20Synthetic%20Voice%20Should%20I%20Choose%20for%20an%20Evocative%20Task.pdf},
year = {2015},
date = {2015-09-01},
booktitle = {Proceeding of SIGDIAL 2015},
pages = {105 – 113},
address = {Prague, Czech Republic},
abstract = {We explore different evaluation methods for 4 different synthetic voices and 1 human voice. We investigate whether intelligibility, naturalness, or likability of a voice is correlated to the voice’s evocative function potential, a measure of the voice’s ability to evoke an intended reaction from the listener. We also investigate the extent to which naturalness and likability ratings vary depending on whether or not exposure to a voice is extended and continuous vs. short-term and sporadic (interleaved with other voices). Finally, we show that an automatic test can replace the standard intelligibility tests for text-to-speech (TTS) systems, which eliminates the need to hire humans to performtranscription tasks saving both time and money.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We explore different evaluation methods for 4 different synthetic voices and 1 human voice. We investigate whether intelligibility, naturalness, or likability of a voice is correlated to the voice’s evocative function potential, a measure of the voice’s ability to evoke an intended reaction from the listener. We also investigate the extent to which naturalness and likability ratings vary depending on whether or not exposure to a voice is extended and continuous vs. short-term and sporadic (interleaved with other voices). Finally, we show that an automatic test can replace the standard intelligibility tests for text-to-speech (TTS) systems, which eliminates the need to hire humans to performtranscription tasks saving both time and money.
137.
Eskenazi, Maxine; Black, Alan W.; Lee, Sungjin; Traum, David
THE REAL CHALLENGE 2014: PROGRESS AND PROSPECTS Proceedings Article
In: Proceeding of SIGDIAL 2015, pp. 209 – 216, 2015.
@inproceedings{eskenazi_real_2015,
title = {THE REAL CHALLENGE 2014: PROGRESS AND PROSPECTS},
author = {Maxine Eskenazi and Alan W. Black and Sungjin Lee and David Traum},
url = {http://ict.usc.edu/pubs/THE%20REAL%20CHALLENGE%202014-PROGRESS%20AND%20PROSPECTS.pdf},
year = {2015},
date = {2015-09-01},
booktitle = {Proceeding of SIGDIAL 2015},
pages = {209 – 216},
abstract = {The REAL Challenge took place for the first time in 2014, with a long term goal of creating streams of real data that the research community can use, by fostering the creation of systems that are capable of attracting real users. A novel approach is to have high school and undergraduate students devise the types of applications that would attract many real users and that need spoken interaction. The projects are presented to researchers from the spoken dialog research community and the researchers and students work together to refine and develop the ideas. Eleven projects were presented at the first workshop. Many of them have found mentors to help in the next stages of the projects. The students have also brought out issues in the use of speech for real applications. Those issues involve privacy and significant personalization of the applications. While long-term impact of the challenge remains to be seen, the challenge has already been a success at its immediate aims of bringing new ideas and new researchers into the community, and serves as a model for related outreach efforts.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The REAL Challenge took place for the first time in 2014, with a long term goal of creating streams of real data that the research community can use, by fostering the creation of systems that are capable of attracting real users. A novel approach is to have high school and undergraduate students devise the types of applications that would attract many real users and that need spoken interaction. The projects are presented to researchers from the spoken dialog research community and the researchers and students work together to refine and develop the ideas. Eleven projects were presented at the first workshop. Many of them have found mentors to help in the next stages of the projects. The students have also brought out issues in the use of speech for real applications. Those issues involve privacy and significant personalization of the applications. While long-term impact of the challenge remains to be seen, the challenge has already been a success at its immediate aims of bringing new ideas and new researchers into the community, and serves as a model for related outreach efforts.
138.
Hiraoka, Takuya; Georgila, Kallirroi; Nouri, Elnaz; Traum, David; Nakamura, Satoshi
Reinforcement Learning in Multi-Party Trading Dialog Proceedings Article
In: Proceeding of SIGDIAL 2015, pp. 32 – 41, Prague, Czech Republic, 2015.
@inproceedings{hiraoka_reinforcement_2015,
title = {Reinforcement Learning in Multi-Party Trading Dialog},
author = {Takuya Hiraoka and Kallirroi Georgila and Elnaz Nouri and David Traum and Satoshi Nakamura},
url = {http://ict.usc.edu/pubs/Reinforcement%20Learning%20in%20Multi-Party%20Trading%20Dialog.pdf},
year = {2015},
date = {2015-09-01},
booktitle = {Proceeding of SIGDIAL 2015},
pages = {32 – 41},
address = {Prague, Czech Republic},
abstract = {In this paper, we apply reinforcement learning (RL) to a multi-party trading scenario where the dialog system (learner) trades with one, two, or three other agents.We experiment with different RL algorithms and reward functions. The negotiation strategy of the learner is learned through simulated dialog with trader simulators. In our experiments, we evaluate how the performance of the learner varies depending on the RL algorithm used and the number of traders. Our results show that (1) even in simple multi-party trading dialog tasks, learning an effective negotiation policy is a very hard problem; and (2) the use of neural fitted Q iteration combined with an incremental reward function produces negotiation policies as effective or even better than the policies of two strong hand-crafted baselines.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we apply reinforcement learning (RL) to a multi-party trading scenario where the dialog system (learner) trades with one, two, or three other agents.We experiment with different RL algorithms and reward functions. The negotiation strategy of the learner is learned through simulated dialog with trader simulators. In our experiments, we evaluate how the performance of the learner varies depending on the RL algorithm used and the number of traders. Our results show that (1) even in simple multi-party trading dialog tasks, learning an effective negotiation policy is a very hard problem; and (2) the use of neural fitted Q iteration combined with an incremental reward function produces negotiation policies as effective or even better than the policies of two strong hand-crafted baselines.
139.
Stratou, Giota; Morency, Louis-Philippe; DeVault, David; Hartholt, Arno; Fast, Edward; Lhommet, Margaux; Lucas, Gale; Morbini, Fabrizio; Georgila, Kallirroi; Scherer, Stefan; Gratch, Jonathan; Stacy, Marcella; Traum, David; Rizzo, Albert
A Demonstration of the Perception System in SimSensei, a Virtual Human Application for Healthcare Interviews Proceedings Article
In: Affective Computing and Intelligent Interaction (ACII), 2015 International Conference on, pp. 787–789, IEEE, Xi'an, China, 2015.
@inproceedings{stratou_demonstration_2015,
title = {A Demonstration of the Perception System in SimSensei, a Virtual Human Application for Healthcare Interviews},
author = {Giota Stratou and Louis-Philippe Morency and David DeVault and Arno Hartholt and Edward Fast and Margaux Lhommet and Gale Lucas and Fabrizio Morbini and Kallirroi Georgila and Stefan Scherer and Jonathan Gratch and Marcella Stacy and David Traum and Albert Rizzo},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7344661},
doi = {10.1109/ACII.2015.7344661},
year = {2015},
date = {2015-09-01},
booktitle = {Affective Computing and Intelligent Interaction (ACII), 2015 International Conference on},
pages = {787–789},
publisher = {IEEE},
address = {Xi'an, China},
abstract = {We present the SimSensei system, a fully automatic virtual agent that conducts interviews to assess indicators of psychological distress. With this demo, we focus our attention on the perception part of the system, a multimodal framework which captures and analyzes user state behavior for both behavioral understanding and interactional purposes. We will demonstrate real-time user state sensing as a part of the SimSensei architecture and discuss how this technology enabled automatic analysis of behaviors related to psychological distress.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present the SimSensei system, a fully automatic virtual agent that conducts interviews to assess indicators of psychological distress. With this demo, we focus our attention on the perception part of the system, a multimodal framework which captures and analyzes user state behavior for both behavioral understanding and interactional purposes. We will demonstrate real-time user state sensing as a part of the SimSensei architecture and discuss how this technology enabled automatic analysis of behaviors related to psychological distress.
140.
Kang, Sin-Hwa; Feng, Andrew; Leuski, Anton; Casas, Dan; Shapiro, Ari
Smart Mobile Virtual Humans: “Chat with Me!” Proceedings Article
In: Proceedings of the 15th International Conference on Intelligent Virtual Agents (IVA), pp. 475–478, Springer, Delft, Netherlands, 2015.
@inproceedings{kang_smart_2015,
title = {Smart Mobile Virtual Humans: “Chat with Me!”},
author = {Sin-Hwa Kang and Andrew Feng and Anton Leuski and Dan Casas and Ari Shapiro},
url = {http://ict.usc.edu/pubs/Smart%20Mobile%20Virtual%20Humans%20-%20Chat%20with%20Me.pdf},
doi = {10.1007/978-3-319-21996-7},
year = {2015},
date = {2015-08-01},
booktitle = {Proceedings of the 15th International Conference on Intelligent Virtual Agents (IVA)},
pages = {475–478},
publisher = {Springer},
address = {Delft, Netherlands},
abstract = {In this study, we are interested in exploring whether people would talk with 3D animated virtual humans using a smartphone for a longer amount of time as a sign of feeling rapport [5], compared to non-animated or audio-only characters in everyday life. Based on previous studies [2, 7, 10], users prefer animated characters in emotionally engaged interactions when the characters were displayed on mobile devices, yet in a lab setting. We aimed to reach a broad range of users outside of the lab in natural settings to investigate the potential of our virtual human on smartphones to facilitate casual, yet emotionally engaging conversation. We also found that the literature has not reached a consensus regarding the ideal gaze patterns for a virtual human, one thing researchers agree on is that inappropriate gaze could negatively impact conversations at times, even worse than receiving no visual feedback at all [1, 4]. Everyday life may bring the experience of awkwardness or uncomfortable sentiments in reaction to continuous mutual gaze. On the other hand, gaze aversion could also make a speaker think their partner is not listening. Our work further aims to address this question of what constitutes appropriate eye gaze in emotionally engaged interactions. We developed a 3D animated and chat-based virtual human which presented emotionally expressive nonverbal behaviors such as facial expressions, head gestures, gaze, and other upper body movements (see Figure 1). The virtual human displayed appropriate gaze that was either consisted of constant mutual gaze or gaze aversion based on a statistical model of saccadic eye movement [8] while listening. Both gaze patterns were accompanied by other forms of appropriate nonverbal feedback. To explore the question of optimal communicative medium, we distributed our virtual human application to users via an app store for Android-powered phones (i.e. Google Play Store) in order to target users who owned a smartphone and could use our application in various natural settings.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this study, we are interested in exploring whether people would talk with 3D animated virtual humans using a smartphone for a longer amount of time as a sign of feeling rapport [5], compared to non-animated or audio-only characters in everyday life. Based on previous studies [2, 7, 10], users prefer animated characters in emotionally engaged interactions when the characters were displayed on mobile devices, yet in a lab setting. We aimed to reach a broad range of users outside of the lab in natural settings to investigate the potential of our virtual human on smartphones to facilitate casual, yet emotionally engaging conversation. We also found that the literature has not reached a consensus regarding the ideal gaze patterns for a virtual human, one thing researchers agree on is that inappropriate gaze could negatively impact conversations at times, even worse than receiving no visual feedback at all [1, 4]. Everyday life may bring the experience of awkwardness or uncomfortable sentiments in reaction to continuous mutual gaze. On the other hand, gaze aversion could also make a speaker think their partner is not listening. Our work further aims to address this question of what constitutes appropriate eye gaze in emotionally engaged interactions. We developed a 3D animated and chat-based virtual human which presented emotionally expressive nonverbal behaviors such as facial expressions, head gestures, gaze, and other upper body movements (see Figure 1). The virtual human displayed appropriate gaze that was either consisted of constant mutual gaze or gaze aversion based on a statistical model of saccadic eye movement [8] while listening. Both gaze patterns were accompanied by other forms of appropriate nonverbal feedback. To explore the question of optimal communicative medium, we distributed our virtual human application to users via an app store for Android-powered phones (i.e. Google Play Store) in order to target users who owned a smartphone and could use our application in various natural settings.
Filter
2008
Miyao, Yusuke; Sagae, Kenji; Sætre, Rune; Matsuzaki, Takuya; Tsujii, Jun'ichi
Evaluating contributions of natural language parsers to protein-protein interaction extraction Journal Article
In: Bioinformatics, vol. 25, no. 3, pp. 394–400, 2008.
Abstract | Links | BibTeX | Tags:
@article{miyao_evaluating_2008,
title = {Evaluating contributions of natural language parsers to protein-protein interaction extraction},
author = {Yusuke Miyao and Kenji Sagae and Rune Sætre and Takuya Matsuzaki and Jun'ichi Tsujii},
url = {http://ict.usc.edu/pubs/Evaluating%20contributions%20of%20natural%20language%20parsers%20to%20protein–protein%20interaction%20extraction.pdf},
year = {2008},
date = {2008-12-01},
journal = {Bioinformatics},
volume = {25},
number = {3},
pages = {394–400},
abstract = {Motivation: While text mining technologies for biomedical research have gained popularity as a way to take advantage of the explosive growth of information in text form in biomedical papers, selecting appropriate natural language processing (NLP) tools is still difficult for researchers who are not familiar with recent advances in NLP. This article provides a comparative evaluation of several state-of-the-art natural language parsers, focusing on the task of extracting protein– protein interaction (PPI) from biomedical papers. We measure how each parser, and its output representation, contributes to accuracy improvement when the parser is used as a component in a PPI system. Results: All the parsers attained improvements in accuracy of PPI extraction. The levels of accuracy obtained with these different parsers vary slightly, while differences in parsing speed are larger. The best accuracy in this work was obtained when we combined Miyao and Tsujii's Enju parser and Charniak and Johnson's reranking parser, and the accuracy is better than the state-of-the-art results on the same data. Availability: The PPI extraction system used in this work (AkanePPI) is available online at http://www-tsujii.is.s.u-tokyo.ac.jp/ downloads/downloads.cgi. The evaluated parsers are also available online from each developer's site.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Motivation: While text mining technologies for biomedical research have gained popularity as a way to take advantage of the explosive growth of information in text form in biomedical papers, selecting appropriate natural language processing (NLP) tools is still difficult for researchers who are not familiar with recent advances in NLP. This article provides a comparative evaluation of several state-of-the-art natural language parsers, focusing on the task of extracting protein– protein interaction (PPI) from biomedical papers. We measure how each parser, and its output representation, contributes to accuracy improvement when the parser is used as a component in a PPI system. Results: All the parsers attained improvements in accuracy of PPI extraction. The levels of accuracy obtained with these different parsers vary slightly, while differences in parsing speed are larger. The best accuracy in this work was obtained when we combined Miyao and Tsujii's Enju parser and Charniak and Johnson's reranking parser, and the accuracy is better than the state-of-the-art results on the same data. Availability: The PPI extraction system used in this work (AkanePPI) is available online at http://www-tsujii.is.s.u-tokyo.ac.jp/ downloads/downloads.cgi. The evaluated parsers are also available online from each developer's site.
Artstein, Ron; Poesio, Massimo
Inter-Coder Agreement for Computational Linguistics Journal Article
In: Computational Linguistics, vol. 34, no. 4, pp. 555–596, 2008.
Abstract | Links | BibTeX | Tags:
@article{artstein_inter-coder_2008,
title = {Inter-Coder Agreement for Computational Linguistics},
author = {Ron Artstein and Massimo Poesio},
url = {http://ict.usc.edu/pubs/Inter-Coder%20Agreement%20for%20Computational%20Linguistics.pdf},
year = {2008},
date = {2008-12-01},
journal = {Computational Linguistics},
volume = {34},
number = {4},
pages = {555–596},
abstract = {This article is a survey of methods for measuring agreement among corpus annotators. It exposes the mathematics and underlying assumptions of agreement coefficients, covering Krippendorff's alpha as well as Scott's pi and Cohen's kappa; discusses the use of coefficients in several annotation tasks; and argues that weighted, alpha-like coefficients, traditionally less used than kappa-like measures in Computational Linguistics, may be more appropriate for many corpus annotation tasks – but that their use makes the interpretation of the value of the coefficient even harder.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This article is a survey of methods for measuring agreement among corpus annotators. It exposes the mathematics and underlying assumptions of agreement coefficients, covering Krippendorff's alpha as well as Scott's pi and Cohen's kappa; discusses the use of coefficients in several annotation tasks; and argues that weighted, alpha-like coefficients, traditionally less used than kappa-like measures in Computational Linguistics, may be more appropriate for many corpus annotation tasks – but that their use makes the interpretation of the value of the coefficient even harder.
Leuski, Anton; Traum, David
A Statistical Approach for Text Processing in Virtual Humans Proceedings Article
In: Proceedings of the 26th Army Science Conference, Orlando, FL, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{leuski_statistical_2008,
title = {A Statistical Approach for Text Processing in Virtual Humans},
author = {Anton Leuski and David Traum},
url = {http://ict.usc.edu/pubs/A%20STATISTICAL%20APPROACH%20FOR%20TEXT%20PROCESSING%20IN%20VIRTUAL%20HUMANS.pdf},
year = {2008},
date = {2008-12-01},
booktitle = {Proceedings of the 26th Army Science Conference},
address = {Orlando, FL},
abstract = {We describe a text classi⬚cation approach based on statistical language modeling. We show how this approach can be used for several natural language processing tasks in a virtual human system. Speci⬚cally, we show it can applied to language understanding, language generation, and character response selection tasks. We illustrate these applications with some experimental results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We describe a text classi⬚cation approach based on statistical language modeling. We show how this approach can be used for several natural language processing tasks in a virtual human system. Speci⬚cally, we show it can applied to language understanding, language generation, and character response selection tasks. We illustrate these applications with some experimental results.
Artstein, Ron; Cannon, Jacob; Gandhe, Sudeep; Gerten, Jillian; Henderer, Joe; Leuski, Anton; Traum, David
Coherence of Off-Topic Response for a Virtual Character Proceedings Article
In: Proceedings of the 26th Army Science Conference, Orlando, FL, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{artstein_coherence_2008,
title = {Coherence of Off-Topic Response for a Virtual Character},
author = {Ron Artstein and Jacob Cannon and Sudeep Gandhe and Jillian Gerten and Joe Henderer and Anton Leuski and David Traum},
url = {http://ict.usc.edu/pubs/COHERENCE%20OF%20OFF-TOPIC%20RESPONSES%20FOR%20A%20VIRTUAL%20CHARACTER.pdf},
year = {2008},
date = {2008-12-01},
booktitle = {Proceedings of the 26th Army Science Conference},
address = {Orlando, FL},
abstract = {We demonstrate three classes of off-topic responses which allow a virtual question-answering character to handle cases where it does not understand the user's input: ask for clarification, indicate misunderstanding, and move on with the conversation. While falling short of full dialogue management, a combination of such responses together with prompts to change the topic can improve overall dialogue coherence.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We demonstrate three classes of off-topic responses which allow a virtual question-answering character to handle cases where it does not understand the user's input: ask for clarification, indicate misunderstanding, and move on with the conversation. While falling short of full dialogue management, a combination of such responses together with prompts to change the topic can improve overall dialogue coherence.
Poesio, Massimo; Artstein, Ron
Introduction to the Special Issue on Ambiguity and Semantic Judgments Journal Article
In: Research on Language and Computation, vol. 6, no. 3-4, pp. 241–245, 2008.
@article{poesio_introduction_2008,
title = {Introduction to the Special Issue on Ambiguity and Semantic Judgments},
author = {Massimo Poesio and Ron Artstein},
url = {http://ict.usc.edu/pubs/Introduction%20to%20the%20Special%20Issue%20on%20Ambiguity%20and%20Semantic%20Judgments.pdf},
year = {2008},
date = {2008-12-01},
journal = {Research on Language and Computation},
volume = {6},
number = {3-4},
pages = {241–245},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Traum, David; Gratch, Jonathan; Hartholt, Arno; Marsella, Stacy C.; Lee, Jina
Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents Proceedings Article
In: Proceedings of the 8th International Conference on Intelligent Virtual Agents, pp. 117–130, Tokyo, Japan, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{traum_multi-party_2008,
title = {Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents},
author = {David Traum and Jonathan Gratch and Arno Hartholt and Stacy C. Marsella and Jina Lee},
url = {http://ict.usc.edu/pubs/Multi-party,%20Multi-issue,%20Multi-strategy%20Negotiation.pdf},
year = {2008},
date = {2008-09-01},
booktitle = {Proceedings of the 8th International Conference on Intelligent Virtual Agents},
pages = {117–130},
address = {Tokyo, Japan},
abstract = {We present a model of negotiation for virtual agents that extends previous work to be more human-like and applicable to a broader range of situations, including more than two negotiators with different goals, and negotiating over multiple options. The agents can dynamically change their negotiating strategies based on the current values of several parameters and factors that can be updated in the course of the negotiation.We have implemented this model and done preliminary evaluation within a prototype training system and a three-party negotiation with two virtual humans and one human.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a model of negotiation for virtual agents that extends previous work to be more human-like and applicable to a broader range of situations, including more than two negotiators with different goals, and negotiating over multiple options. The agents can dynamically change their negotiating strategies based on the current values of several parameters and factors that can be updated in the course of the negotiation.We have implemented this model and done preliminary evaluation within a prototype training system and a three-party negotiation with two virtual humans and one human.
Gandhe, Sudeep; DeVault, David; Roque, Antonio; Martinovski, Bilyana; Artstein, Ron; Leuski, Anton; Gerten, Jillian; Traum, David
From Domain Specification to Virtual Humans: An integrated approach to authoring tactical questioning characters Proceedings Article
In: Proceedings of InterSpeech, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{gandhe_domain_2008,
title = {From Domain Specification to Virtual Humans: An integrated approach to authoring tactical questioning characters},
author = {Sudeep Gandhe and David DeVault and Antonio Roque and Bilyana Martinovski and Ron Artstein and Anton Leuski and Jillian Gerten and David Traum},
url = {http://ict.usc.edu/pubs/From%20Domain%20Specification%20to%20Virtual%20Humans.pdf},
year = {2008},
date = {2008-09-01},
booktitle = {Proceedings of InterSpeech},
abstract = {We present a new approach for rapidly developing dialogue capabilities for virtual humans. Starting from domain specification, an integrated authoring interface automatically generates dialogue acts with all possible contents.These dialogue acts are linked to example utterances in order to provide training data for natural language understanding and generation. The virtual human dialogue system contains a dialogue manager following the information-state approach, using finite-state machines and SCXML to manage local coherence, as well as explicit modeling of emotions and compliance level and a grounding component based on evidence of understanding. Using the authoring tools, we design and implement a version of the virtual human Hassan and compare to previous architectures for the character.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a new approach for rapidly developing dialogue capabilities for virtual humans. Starting from domain specification, an integrated authoring interface automatically generates dialogue acts with all possible contents.These dialogue acts are linked to example utterances in order to provide training data for natural language understanding and generation. The virtual human dialogue system contains a dialogue manager following the information-state approach, using finite-state machines and SCXML to manage local coherence, as well as explicit modeling of emotions and compliance level and a grounding component based on evidence of understanding. Using the authoring tools, we design and implement a version of the virtual human Hassan and compare to previous architectures for the character.
Sagae, Kenji; Tsujii, Jun'ichi
Shift-reduce dependency DAG parsing Proceedings Article
In: 22nd International Conference on Computational Linguistics (Coling 2008), Manchester, UK, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{sagae_shift-reduce_2008,
title = {Shift-reduce dependency DAG parsing},
author = {Kenji Sagae and Jun'ichi Tsujii},
url = {http://www.ict.usc.edu/pubs/Shift-reduce%20dependency%20DAG%20parsing.pdf},
year = {2008},
date = {2008-08-01},
booktitle = {22nd International Conference on Computational Linguistics (Coling 2008)},
address = {Manchester, UK},
abstract = {Most data-driven dependency parsing approaches assume that sentence structure is represented as trees. Although trees have several desirable properties from both computational and linguistic perspectives, the structure of linguistic phenomena that goes beyond shallow syntax often cannot be fully captured by tree representations. We present a parsing approach that is nearly as simple as current data-driven transition-based dependency parsing frameworks, but outputs directed acyclic graphs (DAGs). We demonstrate the benefits of DAG parsing in two experiments where its advantages over dependency tree parsing can be clearly observed: predicate-argument analysis of English and syntactic analysis of Danish with a representation that includes long-distance dependencies and anaphoric reference links.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Most data-driven dependency parsing approaches assume that sentence structure is represented as trees. Although trees have several desirable properties from both computational and linguistic perspectives, the structure of linguistic phenomena that goes beyond shallow syntax often cannot be fully captured by tree representations. We present a parsing approach that is nearly as simple as current data-driven transition-based dependency parsing frameworks, but outputs directed acyclic graphs (DAGs). We demonstrate the benefits of DAG parsing in two experiments where its advantages over dependency tree parsing can be clearly observed: predicate-argument analysis of English and syntactic analysis of Danish with a representation that includes long-distance dependencies and anaphoric reference links.
Roque, Antonio; Traum, David
Degrees of Grounding Based on Evidence of Understanding Proceedings Article
In: 9th SIGdial Workshop on Discourse and Dialogue, Columbus, OH, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{roque_degrees_2008,
title = {Degrees of Grounding Based on Evidence of Understanding},
author = {Antonio Roque and David Traum},
url = {http://ict.usc.edu/pubs/Degrees%20of%20Grounding%20Based%20on%20Evidence%20of%20Understanding.pdf},
year = {2008},
date = {2008-06-01},
booktitle = {9th SIGdial Workshop on Discourse and Dialogue},
address = {Columbus, OH},
abstract = {We introduce the Degrees of Grounding model, which defines the extent to which material being discussed in a dialogue has been grounded. This model has been developed and evaluated by a corpus analysis, and includes a set of types of evidence of understanding, a set of degrees of groundedness, a set of grounding criteria, and methods for identifying each of these. We describe how this model can be used for dialogue management.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We introduce the Degrees of Grounding model, which defines the extent to which material being discussed in a dialogue has been grounded. This model has been developed and evaluated by a corpus analysis, and includes a set of types of evidence of understanding, a set of degrees of groundedness, a set of grounding criteria, and methods for identifying each of these. We describe how this model can be used for dialogue management.
DeVault, David; Traum, David; Artstein, Ron
Making Grammar-Based Generation Easier to Deploy in Dialogue Systems Proceedings Article
In: 9th SIGdial Workshop on Discourse and Dialogue, Columbus, OH, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{devault_making_2008,
title = {Making Grammar-Based Generation Easier to Deploy in Dialogue Systems},
author = {David DeVault and David Traum and Ron Artstein},
url = {http://ict.usc.edu/pubs/Making%20Grammar-Based%20Generation%20Easier%20to%20Deploy%20in%20Dialogue%20Systems%20.pdf},
year = {2008},
date = {2008-06-01},
booktitle = {9th SIGdial Workshop on Discourse and Dialogue},
address = {Columbus, OH},
abstract = {We present a development pipeline and associated algorithms designed to make grammarbased generation easier to deploy in implemented dialogue systems. Our approach realizes a practical trade-off between the capabilities of a system's generation component and the authoring and maintenance burdens imposed on the generation content author for a deployed system. To evaluate our approach, we performed a human rating study with system builders who work on a common largescale spoken dialogue system. Our results demonstrate the viability of our approach and illustrate authoring/performance trade-offs between hand-authored text, our grammar-based approach, and a competing shallow statistical NLG technique},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a development pipeline and associated algorithms designed to make grammarbased generation easier to deploy in implemented dialogue systems. Our approach realizes a practical trade-off between the capabilities of a system's generation component and the authoring and maintenance burdens imposed on the generation content author for a deployed system. To evaluate our approach, we performed a human rating study with system builders who work on a common largescale spoken dialogue system. Our results demonstrate the viability of our approach and illustrate authoring/performance trade-offs between hand-authored text, our grammar-based approach, and a competing shallow statistical NLG technique
DeVault, David; Traum, David; Artstein, Ron
Practical Grammar-Based NLG from Examples Proceedings Article
In: The Fifth International Natural Language Generation Conference (INLG 2008), Salt Fork, OH, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{devault_practical_2008,
title = {Practical Grammar-Based NLG from Examples},
author = {David DeVault and David Traum and Ron Artstein},
url = {http://ict.usc.edu/pubs/Practical%20Grammar-Based%20NLG%20from%20Examples%20.pdf},
year = {2008},
date = {2008-06-01},
booktitle = {The Fifth International Natural Language Generation Conference (INLG 2008)},
address = {Salt Fork, OH},
abstract = {We present a technique that opens up grammar-based generation to a wider range of practical applications by dramatically reducing the development costs and linguistic expertise that are required. Our method infers the grammatical resources needed for generation from a set of declarative examples that link surface expressions directly to the application's available semantic representations. The same examples further serve to optimize a run-time search strategy that generates the best output that can be found within an application-speciï¬c time frame. Our method offers substantially lower development costs than hand-crafted grammars for applicationspeciï¬c NLG, while maintaining high output quality and diversity.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a technique that opens up grammar-based generation to a wider range of practical applications by dramatically reducing the development costs and linguistic expertise that are required. Our method infers the grammatical resources needed for generation from a set of declarative examples that link surface expressions directly to the application's available semantic representations. The same examples further serve to optimize a run-time search strategy that generates the best output that can be found within an application-speciï¬c time frame. Our method offers substantially lower development costs than hand-crafted grammars for applicationspeciï¬c NLG, while maintaining high output quality and diversity.
Gandhe, Sudeep; Traum, David
An Evaluation Understudy for Dialogue Coherence Models Proceedings Article
In: 9th SIGdial Workshop on Discourse and Dialogue, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{gandhe_evaluation_2008,
title = {An Evaluation Understudy for Dialogue Coherence Models},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/An%20Evaluation%20Understudy%20for%20Dialogue%20Coherence%20Models.pdf},
year = {2008},
date = {2008-06-01},
booktitle = {9th SIGdial Workshop on Discourse and Dialogue},
abstract = {Evaluating a dialogue system is seen as a major challenge within the dialogue research community. Due to the very nature of the task, most of the evaluation methods need a substantial amount of human involvement. Following the tradition in machine translation, summarization and discourse coherence modeling, we introduce the the idea of evaluation understudy for dialogue coherence models. Following (Lapata, 2006), we use the information ordering task as a testbed for evaluating dialogue coherence models. This paper reports findings about the reliability of the information ordering task as applied to dialogues. We find that simple n-gram co-occurrence statistics similar in spirit to BLEU (Papineni et al., 2001) correlate very well with human judgments for dialogue coherence.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Evaluating a dialogue system is seen as a major challenge within the dialogue research community. Due to the very nature of the task, most of the evaluation methods need a substantial amount of human involvement. Following the tradition in machine translation, summarization and discourse coherence modeling, we introduce the the idea of evaluation understudy for dialogue coherence models. Following (Lapata, 2006), we use the information ordering task as a testbed for evaluating dialogue coherence models. This paper reports findings about the reliability of the information ordering task as applied to dialogues. We find that simple n-gram co-occurrence statistics similar in spirit to BLEU (Papineni et al., 2001) correlate very well with human judgments for dialogue coherence.
Artstein, Ron; Gandhe, Sudeep; Leuski, Anton; Traum, David
Field Testing of an Interactive Question-Answering Character Proceedings Article
In: International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{artstein_field_2008,
title = {Field Testing of an Interactive Question-Answering Character},
author = {Ron Artstein and Sudeep Gandhe and Anton Leuski and David Traum},
url = {http://ict.usc.edu/pubs/Field%20Testing%20of%20an%20Interactive%20Question-Answering%20Character%20.pdf},
year = {2008},
date = {2008-05-01},
booktitle = {International Conference on Language Resources and Evaluation (LREC)},
address = {Marrakech, Morocco},
abstract = {We tested a life-size embodied question-answering character at a convention where he responded to questions from the audience. The character's responses were then rated for coherence. The ratings, combined with speech transcripts, speech recognition results and the character's responses, allowed us to identify where the character needs to improve, namely in speech recognition and providing off-topic responses.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We tested a life-size embodied question-answering character at a convention where he responded to questions from the audience. The character's responses were then rated for coherence. The ratings, combined with speech transcripts, speech recognition results and the character's responses, allowed us to identify where the character needs to improve, namely in speech recognition and providing off-topic responses.
Hartholt, Arno; Russ, Thomas; Traum, David; Hovy, Eduard; Robinson, Susan
A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture Proceedings Article
In: International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{hartholt_common_2008,
title = {A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture},
author = {Arno Hartholt and Thomas Russ and David Traum and Eduard Hovy and Susan Robinson},
url = {http://ict.usc.edu/pubs/A%20Common%20Ground%20for%20Virtual%20Humans-%20Using%20an%20Ontology%20in%20a%20Natural%20Language%20Oriented%20Virtual%20Human%20Architecture.pdf},
year = {2008},
date = {2008-05-01},
booktitle = {International Conference on Language Resources and Evaluation (LREC)},
address = {Marrakech, Morocco},
abstract = {When dealing with large, distributed systems that use state-of-the-art components, individual components are usually developed in parallel. As development continues, the decoupling invariably leads to a mismatch between how these components internally represent concepts and how they communicate these representations to other components: representations can get out of synch, contain localized errors, or become manageable only by a small group of experts for each module. In this paper, we describe the use of an ontology as part of a complex distributed virtual human architecture in order to enable better communication between modules while improving the overall flexibility needed to change or extend the system. We focus on the natural language understanding capabilities of this architecture and the relationship between language and concepts within the entire system in general and the ontology in particular.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
When dealing with large, distributed systems that use state-of-the-art components, individual components are usually developed in parallel. As development continues, the decoupling invariably leads to a mismatch between how these components internally represent concepts and how they communicate these representations to other components: representations can get out of synch, contain localized errors, or become manageable only by a small group of experts for each module. In this paper, we describe the use of an ontology as part of a complex distributed virtual human architecture in order to enable better communication between modules while improving the overall flexibility needed to change or extend the system. We focus on the natural language understanding capabilities of this architecture and the relationship between language and concepts within the entire system in general and the ontology in particular.
Robinson, Susan; Traum, David; Ittycheriah, Midhun; Henderer, Joe
What would you ask a Conversational Agent? Observations of Human-Agent Dialogues in a Museum Setting Proceedings Article
In: International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{robinson_what_2008,
title = {What would you ask a Conversational Agent? Observations of Human-Agent Dialogues in a Museum Setting},
author = {Susan Robinson and David Traum and Midhun Ittycheriah and Joe Henderer},
url = {http://ict.usc.edu/pubs/What%20would%20you%20ask%20a%20conversational%20agent.pdf},
year = {2008},
date = {2008-05-01},
booktitle = {International Conference on Language Resources and Evaluation (LREC)},
address = {Marrakech, Morocco},
abstract = {Embodied Conversational Agents have typically been constructed for use in limited domain applications, and tested in very specialized environments. Only in recent years have there been more cases of moving agents into wider public applications (e.g. Bell et al., 2003; Kopp et al., 2005). Yet little analysis has been done to determine the differing needs, expectations, and behavior of human users in these environments. With an increasing trend for virtual characters to �go public�, we need to expand our understanding of what this entails for the design and capabilities of our characters. This paper explores these issues through an analysis of a corpus that has been collected since December 2006, from interactions with the virtual character Sgt Blackwell at the Cooper Hewitt Museum in New York. The analysis includes 82 hierarchical categories of user utterances, as well as specific observations on user preferences and behaviors drawn from interactions with Blackwell.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Embodied Conversational Agents have typically been constructed for use in limited domain applications, and tested in very specialized environments. Only in recent years have there been more cases of moving agents into wider public applications (e.g. Bell et al., 2003; Kopp et al., 2005). Yet little analysis has been done to determine the differing needs, expectations, and behavior of human users in these environments. With an increasing trend for virtual characters to �go public�, we need to expand our understanding of what this entails for the design and capabilities of our characters. This paper explores these issues through an analysis of a corpus that has been collected since December 2006, from interactions with the virtual character Sgt Blackwell at the Cooper Hewitt Museum in New York. The analysis includes 82 hierarchical categories of user utterances, as well as specific observations on user preferences and behaviors drawn from interactions with Blackwell.
Poesio, Massimo; Artstein, Ron
Anaphoric Annotation in the ARRAU Corpus Proceedings Article
In: International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{poesio_anaphoric_2008,
title = {Anaphoric Annotation in the ARRAU Corpus},
author = {Massimo Poesio and Ron Artstein},
url = {http://ict.usc.edu/pubs/Anaphoric%20Annotation%20in%20the%20ARRAU%20Corpus.pdf},
year = {2008},
date = {2008-05-01},
booktitle = {International Conference on Language Resources and Evaluation (LREC)},
address = {Marrakech, Morocco},
abstract = {Arrau is a new corpus annotated for anaphoric relations, with information about agreement and explicit representation of multiple antecedents for ambiguous anaphoric expressions and discourse antecedents for expressions which refer to abstract entities such as events, actions and plans. The corpus contains texts from different genres: task-oriented dialogues from the Trains-91 and Trains-93 corpus, narratives from the English Pear Stories corpus, newspaper articles from the Wall Street Journal portion of the Penn Treebank, and mixed text from the Gnome corpus.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Arrau is a new corpus annotated for anaphoric relations, with information about agreement and explicit representation of multiple antecedents for ambiguous anaphoric expressions and discourse antecedents for expressions which refer to abstract entities such as events, actions and plans. The corpus contains texts from different genres: task-oriented dialogues from the Trains-91 and Trains-93 corpus, narratives from the English Pear Stories corpus, newspaper articles from the Wall Street Journal portion of the Penn Treebank, and mixed text from the Gnome corpus.
Lee, Jina; DeVault, David; Marsella, Stacy C.; Traum, David
Thoughts on FML: Behavior Generation in the Virtual Human Communication Architecture Proceedings Article
In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS) First Functional Markup Language Workshop, Estoril, Portugal, 2008.
Abstract | Links | BibTeX | Tags:
@inproceedings{lee_thoughts_2008,
title = {Thoughts on FML: Behavior Generation in the Virtual Human Communication Architecture},
author = {Jina Lee and David DeVault and Stacy C. Marsella and David Traum},
url = {http://ict.usc.edu/pubs/Thoughts%20on%20FML.pdf},
year = {2008},
date = {2008-05-01},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems (AAMAS) First Functional Markup Language Workshop},
address = {Estoril, Portugal},
abstract = {We discuss our current architecture for the generation of natural language and non-verbal behavior in ICT virtual humans. We draw on our experience developing this archi- tecture to present our current perspective on several issues related to the standardization of FML and to the SAIBA framework more generally. In particular, we discuss our current use, and non-use, of FML-inspired representations in generating natural language, eye gaze, and emotional dis- plays. We also comment on some of the shortcomings of our design as currently implemented.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We discuss our current architecture for the generation of natural language and non-verbal behavior in ICT virtual humans. We draw on our experience developing this archi- tecture to present our current perspective on several issues related to the standardization of FML and to the SAIBA framework more generally. In particular, we discuss our current use, and non-use, of FML-inspired representations in generating natural language, eye gaze, and emotional dis- plays. We also comment on some of the shortcomings of our design as currently implemented.
Traum, David; Swartout, William; Gratch, Jonathan; Marsella, Stacy C.
A Virtual Human Dialogue Model for Non-team Interaction Book Section
In: Recent Trends in Discourse and Dialogue, vol. 39, pp. 45–67, Springer, Dordecht, The Netherlands, 2008.
Abstract | Links | BibTeX | Tags:
@incollection{traum_virtual_2008,
title = {A Virtual Human Dialogue Model for Non-team Interaction},
author = {David Traum and William Swartout and Jonathan Gratch and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/A%20Virtual%20Human%20Dialogue%20Model%20for%20Non-team%20Interaction.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Recent Trends in Discourse and Dialogue},
volume = {39},
pages = {45–67},
publisher = {Springer},
address = {Dordecht, The Netherlands},
series = {Text, Speech and Language Technology},
abstract = {We describe the dialogue model for the virtual humans developed at the Institute for Creative Technologies at the University of Southern California. The dialogue model contains a rich set of information state and dialogue moves to allow a wide range of behaviour in multimodal, multiparty interaction. We extend this model to enable non-team negotiation, using ideas from social science literature on negotiation and implemented strategies and dialogue moves for this area. We present a virtual human doctor who uses this model to engage in multimodal negotiation dialogue with people from other organisations. The doctor is part of the SASO-ST system, used for training for non-team interactions.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
We describe the dialogue model for the virtual humans developed at the Institute for Creative Technologies at the University of Southern California. The dialogue model contains a rich set of information state and dialogue moves to allow a wide range of behaviour in multimodal, multiparty interaction. We extend this model to enable non-team negotiation, using ideas from social science literature on negotiation and implemented strategies and dialogue moves for this area. We present a virtual human doctor who uses this model to engage in multimodal negotiation dialogue with people from other organisations. The doctor is part of the SASO-ST system, used for training for non-team interactions.
2007
Kenny, Patrick G.; Hartholt, Arno; Gratch, Jonathan; Swartout, William; Traum, David; Marsella, Stacy C.; Piepol, Diane
Building Interactive Virtual Humans for Training Environments Proceedings Article
In: Interservice/Industry Training, Simulation and Education Conference (I/ITSEC), Orlando, FL, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{kenny_building_2007,
title = {Building Interactive Virtual Humans for Training Environments},
author = {Patrick G. Kenny and Arno Hartholt and Jonathan Gratch and William Swartout and David Traum and Stacy C. Marsella and Diane Piepol},
url = {http://ict.usc.edu/pubs/Building%20Interactive%20Virtual%20Humans%20for%20Training%20Environments.pdf},
year = {2007},
date = {2007-11-01},
booktitle = {Interservice/Industry Training, Simulation and Education Conference (I/ITSEC)},
address = {Orlando, FL},
abstract = {There is a great need in the Joint Forces to have human to human interpersonal training for skills such as negotiation, leadership, interviewing and cultural training. Virtual environments can be incredible training tools if used properly and used for the correct training application. Virtual environments have already been very successful in training Warfighters how to operate vehicles and weapons systems. At the Institute for Creative Technologies (ICT) we have been exploring a new question: can virtual environments be used to train Warfighters in interpersonal skills such as negotiation, tactical questioning and leadership that are so critical for success in the contemporary operating environment? Using embodied conversational agents to create this type of training system has been one of the goals of the Virtual Humans project at the institute. ICT has a great deal of experience building complex, integrated and immersive training systems that address the human factor needs for training experiences. This paper will address the research, technology and value of developing virtual humans for training environments. This research includes speech recognition, natural language understanding & generation, dialogue management, cognitive agents, emotion modeling, question response managers, speech generation and non-verbal behavior. Also addressed will be the diverse set of training environments we have developed for the system, from single computer laptops to multi-computer immersive displays to real and virtual integrated environments. This paper will also discuss the problems, issues and solutions we encountered while building these systems. The paper will recount subject testing we have performed in these environments and results we have obtained from users. Finally the future of this type of Virtual Humans technology and training applications will be discussed.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
There is a great need in the Joint Forces to have human to human interpersonal training for skills such as negotiation, leadership, interviewing and cultural training. Virtual environments can be incredible training tools if used properly and used for the correct training application. Virtual environments have already been very successful in training Warfighters how to operate vehicles and weapons systems. At the Institute for Creative Technologies (ICT) we have been exploring a new question: can virtual environments be used to train Warfighters in interpersonal skills such as negotiation, tactical questioning and leadership that are so critical for success in the contemporary operating environment? Using embodied conversational agents to create this type of training system has been one of the goals of the Virtual Humans project at the institute. ICT has a great deal of experience building complex, integrated and immersive training systems that address the human factor needs for training experiences. This paper will address the research, technology and value of developing virtual humans for training environments. This research includes speech recognition, natural language understanding & generation, dialogue management, cognitive agents, emotion modeling, question response managers, speech generation and non-verbal behavior. Also addressed will be the diverse set of training environments we have developed for the system, from single computer laptops to multi-computer immersive displays to real and virtual integrated environments. This paper will also discuss the problems, issues and solutions we encountered while building these systems. The paper will recount subject testing we have performed in these environments and results we have obtained from users. Finally the future of this type of Virtual Humans technology and training applications will be discussed.
Traum, David; Roque, Antonio; Leuski, Anton; Georgiou, Panayiotis G.; Gerten, Jillian; Martinovski, Bilyana; Narayanan, Shrikanth; Robinson, Susan; Vaswani, Ashish
Hassan: A Virtual Human for Tactical Questioning Proceedings Article
In: 8th SIGdial Workshop on Discourse and Dialogue, Antwerp, Belgium, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{traum_hassan_2007,
title = {Hassan: A Virtual Human for Tactical Questioning},
author = {David Traum and Antonio Roque and Anton Leuski and Panayiotis G. Georgiou and Jillian Gerten and Bilyana Martinovski and Shrikanth Narayanan and Susan Robinson and Ashish Vaswani},
url = {http://ict.usc.edu/pubs/Hassan-%20A%20Virtual%20Human%20for%20Tactical%20Questioning%20.pdf},
year = {2007},
date = {2007-09-01},
booktitle = {8th SIGdial Workshop on Discourse and Dialogue},
address = {Antwerp, Belgium},
abstract = {We present Hassan, a virtual human who engages in Tactical Questioning dialogues. We describe the tactical questioning domain, the motivation for this character, the speciï¬c architecture and present brief examples and an evaluation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present Hassan, a virtual human who engages in Tactical Questioning dialogues. We describe the tactical questioning domain, the motivation for this character, the speciï¬c architecture and present brief examples and an evaluation.
Roque, Antonio; Traum, David
A Model of Compliance and Emotion for Potentially Adversarial Dialogue Agents Proceedings Article
In: 8th SIGdial Workshop on Discourse and Dialogue, Antwerp, Belgium, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{roque_model_2007,
title = {A Model of Compliance and Emotion for Potentially Adversarial Dialogue Agents},
author = {Antonio Roque and David Traum},
url = {http://ict.usc.edu/pubs/A%20Model%20of%20Compliance%20and%20Emotion%20for%20Potentially%20Adversarial%20Dialogue%20%20Agents.pdf},
year = {2007},
date = {2007-09-01},
booktitle = {8th SIGdial Workshop on Discourse and Dialogue},
address = {Antwerp, Belgium},
abstract = {We present a model of compliance, for domains in which a dialogue agent may become adversarial. This model includes a set of emotions and a set of levels of compliance, and strategies for changing these.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a model of compliance, for domains in which a dialogue agent may become adversarial. This model includes a set of emotions and a set of levels of compliance, and strategies for changing these.
Gandhe, Sudeep; Traum, David
Creating Spoken Dialogue Characters from Corpora without Annotations Proceedings Article
In: Interspeech 2007, Antwerp, Belgium, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{gandhe_creating_2007,
title = {Creating Spoken Dialogue Characters from Corpora without Annotations},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/Creating%20Spoken%20Dialogue%20Characters%20from%20Corpora%20without%20Annotations%20.pdf},
year = {2007},
date = {2007-08-01},
booktitle = {Interspeech 2007},
address = {Antwerp, Belgium},
abstract = {Virtual humans are being used in a number of applications, including simulation-based training, multi-player games, and museum kiosks. Natural language dialogue capabilities are an essential part of their human-like persona. These dialogue systems have a goal of being believable and generally have to operate within the bounds of their restricted domains. Most dialogue systems operate on a dialogue-act level and require extensive annotation efforts. Semantic annotation and rule authoring have long been known as bottlenecks for developing dialogue systems for new domains. In this paper, we investigate several dialogue models for virtual humans that are trained on an unannotated human-human corpus. These are inspired by information retrieval and work on the surface text level. We evaluate these in text-based and spoken interactions and also against the upper baseline of human-human dialogues.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Virtual humans are being used in a number of applications, including simulation-based training, multi-player games, and museum kiosks. Natural language dialogue capabilities are an essential part of their human-like persona. These dialogue systems have a goal of being believable and generally have to operate within the bounds of their restricted domains. Most dialogue systems operate on a dialogue-act level and require extensive annotation efforts. Semantic annotation and rule authoring have long been known as bottlenecks for developing dialogue systems for new domains. In this paper, we investigate several dialogue models for virtual humans that are trained on an unannotated human-human corpus. These are inspired by information retrieval and work on the surface text level. We evaluate these in text-based and spoken interactions and also against the upper baseline of human-human dialogues.
Ai, Hua; Roque, Antonio; Leuski, Anton; Traum, David
Using Information State to Improve Dialogue Move Identification in a Spoken Dialogue System Proceedings Article
In: Proceedings of the 10th Interspeech Conference, Antwerp, Belgium, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{ai_using_2007,
title = {Using Information State to Improve Dialogue Move Identification in a Spoken Dialogue System},
author = {Hua Ai and Antonio Roque and Anton Leuski and David Traum},
url = {http://ict.usc.edu/pubs/Using%20Information%20State%20to%20Improve%20Dialogue%20Move%20Identification%20in%20a%20Spoken%20Dialogue%20System.pdf},
year = {2007},
date = {2007-08-01},
booktitle = {Proceedings of the 10th Interspeech Conference},
address = {Antwerp, Belgium},
abstract = {In this paper we investigate how to improve the performance of a dialogue move and parameter tagger for a taskoriented dialogue system using the information-state approach. We use a corpus of utterances and information states from an implemented system to train and evaluate a tagger, and then evaluate the tagger in an on-line system. Use of information state context is shown to improve performance of the system.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we investigate how to improve the performance of a dialogue move and parameter tagger for a taskoriented dialogue system using the information-state approach. We use a corpus of utterances and information states from an implemented system to train and evaluate a tagger, and then evaluate the tagger in an on-line system. Use of information state context is shown to improve performance of the system.
Robinson, Susan; Roque, Antonio; Vaswani, Ashish; Traum, David; Hernandez, Charles; Millspaugh, Bill
Evaluation of a Spoken Dialogue System for Virtual Reality Call for Fire Training Proceedings Article
In: 10th International Pragmatics Conference, Gotenborg, Sweden, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{robinson_evaluation_2007,
title = {Evaluation of a Spoken Dialogue System for Virtual Reality Call for Fire Training},
author = {Susan Robinson and Antonio Roque and Ashish Vaswani and David Traum and Charles Hernandez and Bill Millspaugh},
url = {http://ict.usc.edu/pubs/Evaluation%20of%20a%20Spoken%20Dialogue%20System%20for%20Virtual%20Reality%20Call%20for%20Fire%20Training.pdf},
year = {2007},
date = {2007-07-01},
booktitle = {10th International Pragmatics Conference},
address = {Gotenborg, Sweden},
abstract = {We present an evaluation of a spoken dialogue system that engages in dialogues with soldiers training in an immersive Call for Fire (CFF) simulation. We briefly describe aspects of the Joint Fires and Effects Trainer System, and the Radiobot-CFF dialogue system, which can engage in voice communications with a trainee in call for fire dialogues. An experiment is described to judge performance of the Radiobot CFF system compared with human radio operators. Results show that while the current version of the system is not quite at humanperformance levels, it is already viable for training interaction and as an operator-controller aid.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present an evaluation of a spoken dialogue system that engages in dialogues with soldiers training in an immersive Call for Fire (CFF) simulation. We briefly describe aspects of the Joint Fires and Effects Trainer System, and the Radiobot-CFF dialogue system, which can engage in voice communications with a trainee in call for fire dialogues. An experiment is described to judge performance of the Radiobot CFF system compared with human radio operators. Results show that while the current version of the system is not quite at humanperformance levels, it is already viable for training interaction and as an operator-controller aid.
Kenny, Patrick G.; Hartholt, Arno; Gratch, Jonathan; Traum, David; Marsella, Stacy C.; Swartout, William
The More the Merrier: Multi-Party Negotiation with Virtual Humans Proceedings Article
In: AAAI Conference On Artificial Intelligence; Proceedings of the 22nd National Conference on Artificial Intelligence, pp. 1970–1971, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{kenny_more_2007,
title = {The More the Merrier: Multi-Party Negotiation with Virtual Humans},
author = {Patrick G. Kenny and Arno Hartholt and Jonathan Gratch and David Traum and Stacy C. Marsella and William Swartout},
url = {http://ict.usc.edu/pubs/The%20More%20the%20Merrier-%20Multi-Party%20Negotiation%20with%20Virtual%20Humans.pdf},
year = {2007},
date = {2007-07-01},
booktitle = {AAAI Conference On Artificial Intelligence; Proceedings of the 22nd National Conference on Artificial Intelligence},
volume = {2},
pages = {1970–1971},
abstract = {The goal of the Virtual Humans Project at the University of Southern California�s Institute for Creative Technologies is to enrich virtual training environments with virtual humans � autonomous agents that support face-to-face interaction with trainees in a variety of roles � through bringing together many different areas of research including speech recognition, natural language understanding, dialogue management, cognitive modeling, emotion modeling, non-verbal behavior and speech and knowledge management. The demo at AAAI will focus on our work using virtual humans to train negotiation skills. Conference attendees will negotiate with a virtual human doctor and elder to try to move a clinic out of harm�s way in single and multi-party negotiation scenarios using the latest iteration of our Virtual Humans framework. The user will use natural speech to talk to the embodied agents, who will respond in accordance with their internal task model and state. The characters will carry out a multi-party dialogue with verbal and non-verbal behavior. A video of a single-party version of the scenario was shown at AAAI-06. This new interactive demo introduces several new features, including multi-party negotiation, dynamically generated non-verbal behavior and a central ontology.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The goal of the Virtual Humans Project at the University of Southern California�s Institute for Creative Technologies is to enrich virtual training environments with virtual humans � autonomous agents that support face-to-face interaction with trainees in a variety of roles � through bringing together many different areas of research including speech recognition, natural language understanding, dialogue management, cognitive modeling, emotion modeling, non-verbal behavior and speech and knowledge management. The demo at AAAI will focus on our work using virtual humans to train negotiation skills. Conference attendees will negotiate with a virtual human doctor and elder to try to move a clinic out of harm�s way in single and multi-party negotiation scenarios using the latest iteration of our Virtual Humans framework. The user will use natural speech to talk to the embodied agents, who will respond in accordance with their internal task model and state. The characters will carry out a multi-party dialogue with verbal and non-verbal behavior. A video of a single-party version of the scenario was shown at AAAI-06. This new interactive demo introduces several new features, including multi-party negotiation, dynamically generated non-verbal behavior and a central ontology.
Sagae, Kenji; Tsujii, Jun
Dependency parsing and domain adaptation with data-driven LR models and parser ensembles Proceedings Article
In: Proceedings of the CoNLL 2007 Shared Task. Joint Conferences on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, Czech Republic, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{sagae_dependency_2007,
title = {Dependency parsing and domain adaptation with data-driven LR models and parser ensembles},
author = {Kenji Sagae and Jun Tsujii},
url = {http://ict.usc.edu/pubs/Dependency%20Parsing%20and%20Domain%20Adaptation%20with%20LR%20Models%20and%20Parser%20Ensembles.pdf},
year = {2007},
date = {2007-07-01},
booktitle = {Proceedings of the CoNLL 2007 Shared Task. Joint Conferences on Empirical Methods in Natural Language Processing and Computational Natural Language Learning},
address = {Prague, Czech Republic},
abstract = {We present a data-driven variant of the LR algorithm for dependency parsing, and extend it with a best-first search for probabilistic generalized data-driven LR dependency parsing. Parser actions are determined by a machine learning component, based on features that represent the current state of the parser. We apply this parsing framework to both tracks of the CoNLL 2007 shared task on dependency parsing, in each case taking advantage of multiple models trained with different learners. In the multilingual track, we train three data-driven LR models for each of the ten languages, and combine the analyses obtained with each individual model using a maximum spanning tree voting scheme. In the domain adaptation track, we use two models to parse unlabeled data in the target domain to supplement the labeled training set in the source domain, in a scheme similar to one iteration of co-training.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a data-driven variant of the LR algorithm for dependency parsing, and extend it with a best-first search for probabilistic generalized data-driven LR dependency parsing. Parser actions are determined by a machine learning component, based on features that represent the current state of the parser. We apply this parsing framework to both tracks of the CoNLL 2007 shared task on dependency parsing, in each case taking advantage of multiple models trained with different learners. In the multilingual track, we train three data-driven LR models for each of the ten languages, and combine the analyses obtained with each individual model using a maximum spanning tree voting scheme. In the domain adaptation track, we use two models to parse unlabeled data in the target domain to supplement the labeled training set in the source domain, in a scheme similar to one iteration of co-training.
Jan, Dusan; Traum, David
Dynamic Movement and Positioning of Embodied Agents in Multiparty Conversations Proceedings Article
In: ACL 2007 Workshop on Embodied Language Processing, Prague, Czech Republic, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{jan_dynamic_2007,
title = {Dynamic Movement and Positioning of Embodied Agents in Multiparty Conversations},
author = {Dusan Jan and David Traum},
url = {http://ict.usc.edu/pubs/Dynamic%20Movement%20and%20Positioning%20of%20Embodied%20Agents%20in%20Multiparty%20%20Conversations.pdf},
year = {2007},
date = {2007-06-01},
booktitle = {ACL 2007 Workshop on Embodied Language Processing},
address = {Prague, Czech Republic},
abstract = {For embodied agents to engage in realistic multiparty conversation, they must stand in appropriate places with respect to other agents and the environment. When these factors change, for example when an agent joins a conversation, the agents must dynamically move to a new location and/or orientation to accommodate. This paper presents an algorithm for simulating the movement of agents based on observed human behavior using techniques developed for pedestrian movement in crowd simulations. We extend a previous group conversation simulation to include an agent motion algorithm. We examine several test cases and show how the simulation generates results that mirror real-life conversation settings.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
For embodied agents to engage in realistic multiparty conversation, they must stand in appropriate places with respect to other agents and the environment. When these factors change, for example when an agent joins a conversation, the agents must dynamically move to a new location and/or orientation to accommodate. This paper presents an algorithm for simulating the movement of agents based on observed human behavior using techniques developed for pedestrian movement in crowd simulations. We extend a previous group conversation simulation to include an agent motion algorithm. We examine several test cases and show how the simulation generates results that mirror real-life conversation settings.
Gandhe, Sudeep; Traum, David
First Steps Towards Dialogue Modelling from an Un-annotated Human-Human Corpus Proceedings Article
In: 5th Workshop on Knowledge and Reasoning in Practical Dialogue Systems, Hyderabad, India, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{gandhe_first_2007,
title = {First Steps Towards Dialogue Modelling from an Un-annotated Human-Human Corpus},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/First%20Steps%20towards%20Dialogue%20Modelling%20from%20an%20Un-annotated%20Human-Human%20Corpus.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {5th Workshop on Knowledge and Reasoning in Practical Dialogue Systems},
address = {Hyderabad, India},
abstract = {Virtual human characters equipped with natural language dialogue capability have proved useful in many fields like simulation training and interactive games. Generally behind such dialogue managers lies a complex knowledge-rich rule-based system. Building such system involves meticulous annotation of data and hand autoring of rules. In this paper we build a statistical dialogue model from roleplay and wizard of oz dialog corpus with virtually no annotation. We compare these methods with the tra ditional approaches. We have evaluated these systems for perceived appropriateness of response and the results are presented here.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Virtual human characters equipped with natural language dialogue capability have proved useful in many fields like simulation training and interactive games. Generally behind such dialogue managers lies a complex knowledge-rich rule-based system. Building such system involves meticulous annotation of data and hand autoring of rules. In this paper we build a statistical dialogue model from roleplay and wizard of oz dialog corpus with virtually no annotation. We compare these methods with the tra ditional approaches. We have evaluated these systems for perceived appropriateness of response and the results are presented here.
Kenny, Patrick G.; Parsons, Thomas D.; Gratch, Jonathan; Leuski, Anton; Rizzo, Albert
Virtual Patients for Clinical Therapist Skills Training Proceedings Article
In: Lecture Notes in Artificial Intelligence; Proceedings of the 7th International Conference on Intelligent Virtual Agents (IVA), pp. 197–210, Paris, France, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{kenny_virtual_2007,
title = {Virtual Patients for Clinical Therapist Skills Training},
author = {Patrick G. Kenny and Thomas D. Parsons and Jonathan Gratch and Anton Leuski and Albert Rizzo},
url = {http://ict.usc.edu/pubs/Virtual%20Patients%20for%20Clinical%20Therapist%20Skills%20Training.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {Lecture Notes in Artificial Intelligence; Proceedings of the 7th International Conference on Intelligent Virtual Agents (IVA)},
volume = {4722},
pages = {197–210},
address = {Paris, France},
abstract = {Virtual humans offer an exciting and powerful potential for rich interactive experiences. Fully embodied virtual humans are growing in capability, ease, and utility. As a result, they present an opportunity for expanding research into burgeoning virtual patient medical applications. In this paper we consider the ways in which one may go about building and applying virtual human technology to the virtual patient domain. Specifically we aim to show that virtual human technology may be used to help develop the interviewing and diagnostics skills of developing clinicians. Herein we proffer a description of our iterative design process and preliminary results to show that virtual patients may be a useful adjunct to psychotherapy education.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Virtual humans offer an exciting and powerful potential for rich interactive experiences. Fully embodied virtual humans are growing in capability, ease, and utility. As a result, they present an opportunity for expanding research into burgeoning virtual patient medical applications. In this paper we consider the ways in which one may go about building and applying virtual human technology to the virtual patient domain. Specifically we aim to show that virtual human technology may be used to help develop the interviewing and diagnostics skills of developing clinicians. Herein we proffer a description of our iterative design process and preliminary results to show that virtual patients may be a useful adjunct to psychotherapy education.
Lee, Jina; Marsella, Stacy C.; Traum, David; Gratch, Jonathan; Lance, Brent
The Rickel Gaze Model: A Window on the Mind of a Virtual Human Proceedings Article
In: Lecture Notes in Artificial Intelligence; Proceedings of the 7th International Conference on Intelligent Virtual Agents (IVA), pp. 296–303, Paris, France, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{lee_rickel_2007,
title = {The Rickel Gaze Model: A Window on the Mind of a Virtual Human},
author = {Jina Lee and Stacy C. Marsella and David Traum and Jonathan Gratch and Brent Lance},
url = {http://ict.usc.edu/pubs/The%20Rickel%20Gaze%20Model-%20A%20Window%20on%20the%20Mind%20of%20a%20Virtual%20Human.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {Lecture Notes in Artificial Intelligence; Proceedings of the 7th International Conference on Intelligent Virtual Agents (IVA)},
volume = {4722},
pages = {296–303},
address = {Paris, France},
abstract = {Gaze plays a large number of cognitive, communicative and affective roles in face-to-face human interaction. To build a believable virtual human, it is imperative to construct a gaze model that generates realistic gaze behaviors. However, it is not enough to merely imitate a person's eye movements. The gaze behaviors should reflect the internal states of the virtual human and users should be able to derive them by observing the behaviors. In this paper, we present a gaze model driven by the cognitive operations; the model processes the virtual human's reasoning, dialog management, and goals to generate behaviors that reflect the agent's inner thoughts. It has been implemented in our virtual human system and operates in real-time. The gaze model introduced in this paper was originally designed and developed by Jeff Rickel but has since been extended by the authors.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gaze plays a large number of cognitive, communicative and affective roles in face-to-face human interaction. To build a believable virtual human, it is imperative to construct a gaze model that generates realistic gaze behaviors. However, it is not enough to merely imitate a person's eye movements. The gaze behaviors should reflect the internal states of the virtual human and users should be able to derive them by observing the behaviors. In this paper, we present a gaze model driven by the cognitive operations; the model processes the virtual human's reasoning, dialog management, and goals to generate behaviors that reflect the agent's inner thoughts. It has been implemented in our virtual human system and operates in real-time. The gaze model introduced in this paper was originally designed and developed by Jeff Rickel but has since been extended by the authors.
Martinovski, Bilyana; Traum, David; Marsella, Stacy C.
Rejection of empathy in negotiation Journal Article
In: Group Decision and Negotiation, vol. 16, pp. 61–76, 2007, ISSN: 0926-2644.
Abstract | Links | BibTeX | Tags:
@article{martinovski_rejection_2007,
title = {Rejection of empathy in negotiation},
author = {Bilyana Martinovski and David Traum and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/Rejection%20of%20empathy%20in%20negotiation.pdf},
issn = {0926-2644},
year = {2007},
date = {2007-01-01},
journal = {Group Decision and Negotiation},
volume = {16},
pages = {61–76},
abstract = {Trust is a crucial quality in the development of individuals and societies and empathy plays a key role in the formation of trust. Trust and empathy have growing importance in studies of negotiation. However, empathy can be rejected which complicates its role in negotiation. This paper presents a linguistic analysis of empathy by focusing on rejection of empathy in negotiation. Some of the rejections are due to failed recognition of the rejector's needs and desires whereas others have mainly strategic functions gaining momentum in the negotiation. In both cases, rejection of empathy is a phase in the negotiation not a breakdown.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Trust is a crucial quality in the development of individuals and societies and empathy plays a key role in the formation of trust. Trust and empathy have growing importance in studies of negotiation. However, empathy can be rejected which complicates its role in negotiation. This paper presents a linguistic analysis of empathy by focusing on rejection of empathy in negotiation. Some of the rejections are due to failed recognition of the rejector's needs and desires whereas others have mainly strategic functions gaining momentum in the negotiation. In both cases, rejection of empathy is a phase in the negotiation not a breakdown.
Jan, Dusan; Herrera, David; Martinovski, Bilyana; Novick, David; Traum, David
A Computational Model of Culture-Specific Conversational Behavior Proceedings Article
In: Proceedings of the Intelligent Virtual Humans Conference, Paris, France, 2007.
Abstract | Links | BibTeX | Tags:
@inproceedings{jan_computational_2007,
title = {A Computational Model of Culture-Specific Conversational Behavior},
author = {Dusan Jan and David Herrera and Bilyana Martinovski and David Novick and David Traum},
url = {http://ict.usc.edu/pubs/A%20Computational%20Model%20of%20Culture-Specific%20Conversational%20Behavior.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {Proceedings of the Intelligent Virtual Humans Conference},
address = {Paris, France},
abstract = {This paper presents a model for simulating cultural differences in the conversational behavior of virtual agents. The model provides parameters for differences in proxemics, gaze and overlap in turn taking.We present a review of literature on these factors and show results of a study where native speakers of North American English, Mexican Spanish and Arabic were asked to rate the realism of the simulations generated based on different cultural parameters with respect to their culture.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a model for simulating cultural differences in the conversational behavior of virtual agents. The model provides parameters for differences in proxemics, gaze and overlap in turn taking.We present a review of literature on these factors and show results of a study where native speakers of North American English, Mexican Spanish and Arabic were asked to rate the realism of the simulations generated based on different cultural parameters with respect to their culture.
2006
Leuski, Anton; Lavrenko, Victor
Tracking Dragon-Hunters with Language Models Proceedings Article
In: Conference on Information and Knowledge Management, Arlington, VA, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{leuski_tracking_2006,
title = {Tracking Dragon-Hunters with Language Models},
author = {Anton Leuski and Victor Lavrenko},
url = {http://ict.usc.edu/pubs/Tracking%20Dragon-Hunters%20with%20Language%20Models.pdf},
year = {2006},
date = {2006-11-01},
booktitle = {Conference on Information and Knowledge Management},
address = {Arlington, VA},
abstract = {We are interested in the problem of understanding the connections between human activities and the content of textual information generated in regard to those activities. Massive online collaborative environments, specifically online virtual worlds, where people meet, exchange messages, and perform actions can be a rich source for such an analysis. In this paper we study one of such virtual worlds and the activities of its inhabitants. We explore the existing dependencies between the activities and the content of the chat messages the world's inhabitants exchange with each other. We outline three experimental tasks and show how language modeling and text clustering techniques allow us to explore those dependencies successfully.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We are interested in the problem of understanding the connections between human activities and the content of textual information generated in regard to those activities. Massive online collaborative environments, specifically online virtual worlds, where people meet, exchange messages, and perform actions can be a rich source for such an analysis. In this paper we study one of such virtual worlds and the activities of its inhabitants. We explore the existing dependencies between the activities and the content of the chat messages the world's inhabitants exchange with each other. We outline three experimental tasks and show how language modeling and text clustering techniques allow us to explore those dependencies successfully.
Core, Mark; Traum, David; Lane, H. Chad; Swartout, William; Marsella, Stacy C.; Gratch, Jonathan; Lent, Michael
Teaching Negotiation Skills through Practice and Reflection with Virtual Humans Journal Article
In: Simulation: Transactions of the Society for Modeling and Simulation, vol. 82, no. 11, pp. 685–701, 2006.
Abstract | Links | BibTeX | Tags:
@article{core_teaching_2006,
title = {Teaching Negotiation Skills through Practice and Reflection with Virtual Humans},
author = {Mark Core and David Traum and H. Chad Lane and William Swartout and Stacy C. Marsella and Jonathan Gratch and Michael Lent},
url = {http://ict.usc.edu/pubs/Teaching%20Negotiation%20Skills.pdf},
year = {2006},
date = {2006-11-01},
journal = {Simulation: Transactions of the Society for Modeling and Simulation},
volume = {82},
number = {11},
pages = {685–701},
abstract = {Although the representation of physical environments and behaviors will continue to play an important role in simulation-based training, an emerging challenge is the representation of virtual humans with rich mental models (e.g., including emotions, trust) that interact through conversational as well as physical behaviors. The motivation for such simulations is training soft skills such as leadership, cultural awareness, and negotiation, where the majority of actions are conversational, and the problem solving involves consideration of the emotions, attitudes, and desires of others.The educational power of such simulations can be enhanced by the integration of an intelligent tutoring system to support learners� understanding of the effect of their actions on virtual humans and how they might improve their performance. In this paper, we discuss our efforts to build such virtual humans, along with an accompanying intelligent tutor, for the domain of negotiation and cultural awareness.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Although the representation of physical environments and behaviors will continue to play an important role in simulation-based training, an emerging challenge is the representation of virtual humans with rich mental models (e.g., including emotions, trust) that interact through conversational as well as physical behaviors. The motivation for such simulations is training soft skills such as leadership, cultural awareness, and negotiation, where the majority of actions are conversational, and the problem solving involves consideration of the emotions, attitudes, and desires of others.The educational power of such simulations can be enhanced by the integration of an intelligent tutoring system to support learners� understanding of the effect of their actions on virtual humans and how they might improve their performance. In this paper, we discuss our efforts to build such virtual humans, along with an accompanying intelligent tutor, for the domain of negotiation and cultural awareness.
Leuski, Anton; Kennedy, Brandon; Patel, Ronakkumar; Traum, David
Asking Questions to Limited Domain Virtual Characters: How Good Does Speech Recognition Have to Be? Proceedings Article
In: Proceedings of the 25th Army Science Conference, Orlando, FL, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{leuski_asking_2006,
title = {Asking Questions to Limited Domain Virtual Characters: How Good Does Speech Recognition Have to Be?},
author = {Anton Leuski and Brandon Kennedy and Ronakkumar Patel and David Traum},
url = {http://ict.usc.edu/pubs/Asking%20Questions%20to%20Limited%20Domain%20Virtual%20Characters.pdf},
year = {2006},
date = {2006-11-01},
booktitle = {Proceedings of the 25th Army Science Conference},
address = {Orlando, FL},
abstract = {In this paper, we describe the evaluation of a limited domain question-answering characters, particularly as to the effect of non-optimal speech recognition, and the ability to appropriately answer novel questions. Results show that answering ability is robust until speech recognition reaches over 60% Word error rate.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we describe the evaluation of a limited domain question-answering characters, particularly as to the effect of non-optimal speech recognition, and the ability to appropriately answer novel questions. Results show that answering ability is robust until speech recognition reaches over 60% Word error rate.
Hill, Randall W.; Kim, Julia; Zbylut, MIchelle L.; Gordon, Andrew S.; Traum, David; Gandhe, Sudeep; King, Stewart; Lavis, Salvo; Rocher, Scott
AXL.Net: Web-enabled Case Method Instruction for Accelerating Tacit Knowledge Acquisition in Leaders Proceedings Article
In: Proceedings of the 25th Army Science Conference, Orlando, FL, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{hill_axlnet_2006,
title = {AXL.Net: Web-enabled Case Method Instruction for Accelerating Tacit Knowledge Acquisition in Leaders},
author = {Randall W. Hill and Julia Kim and MIchelle L. Zbylut and Andrew S. Gordon and David Traum and Sudeep Gandhe and Stewart King and Salvo Lavis and Scott Rocher},
url = {http://ict.usc.edu/pubs/AXLNet-%20Web-enabled%20Case%20Method%20Instruction%20for%20Accelerating%20Tacit%20Knowledge%20Acquisition%20in%20Leaders.PDF},
year = {2006},
date = {2006-11-01},
booktitle = {Proceedings of the 25th Army Science Conference},
address = {Orlando, FL},
abstract = {AXL.Net is a prototype web-based immersive technology solution that supports case method teaching for U.S. Army leader development. The AXL.Net system addresses three challenges: (1) designing a pedagogicallysound research prototype for leader development, (2) integrating research technologies with the best of Web 2.0 innovations to enhance case method teaching, and (3) providing an easy to use system. Initial evaluations show that the prototype application and framework is effective for leader development.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
AXL.Net is a prototype web-based immersive technology solution that supports case method teaching for U.S. Army leader development. The AXL.Net system addresses three challenges: (1) designing a pedagogicallysound research prototype for leader development, (2) integrating research technologies with the best of Web 2.0 innovations to enhance case method teaching, and (3) providing an easy to use system. Initial evaluations show that the prototype application and framework is effective for leader development.
Roque, Antonio; Leuski, Anton; Rangarajan, Vivek; Robinson, Susan; Vaswani, Ashish; Narayanan, Shrikanth; Traum, David
Radiobot-CFF: A Spoken Dialogue System for Military Training Proceedings Article
In: Interspeech 2006, Pittsburgh, PA, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{roque_radiobot-cff_2006,
title = {Radiobot-CFF: A Spoken Dialogue System for Military Training},
author = {Antonio Roque and Anton Leuski and Vivek Rangarajan and Susan Robinson and Ashish Vaswani and Shrikanth Narayanan and David Traum},
url = {http://ict.usc.edu/pubs/Radiobot-CFF-%20A%20Spoken%20Dialogue%20System%20for%20Military%20Training.pdf},
year = {2006},
date = {2006-09-01},
booktitle = {Interspeech 2006},
address = {Pittsburgh, PA},
abstract = {We describe a spoken dialogue system which can engage in Call For Fire (CFF) radio dialogues to help train soldiers in proper procedures for requesting artillery fire missions. We describethe domain, an information-state dialogue manager with a novel system of interactive information components, and provide evaluation results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We describe a spoken dialogue system which can engage in Call For Fire (CFF) radio dialogues to help train soldiers in proper procedures for requesting artillery fire missions. We describethe domain, an information-state dialogue manager with a novel system of interactive information components, and provide evaluation results.
Tepperman, Joseph; Traum, David; Narayanan, Shrikanth
"Yeah Right": Sarcasm Recognition for Spoken Dialogue Systems Proceedings Article
In: Interspeech 2006, Pittsburgh, PA, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{tepperman_yeah_2006,
title = {"Yeah Right": Sarcasm Recognition for Spoken Dialogue Systems},
author = {Joseph Tepperman and David Traum and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Yeah%20Right-%20Sarcasm%20Recognition%20for%20Spoken%20Dialogue%20Systems.pdf},
year = {2006},
date = {2006-09-01},
booktitle = {Interspeech 2006},
address = {Pittsburgh, PA},
abstract = {The robust understanding of sarcasm in a spoken dialogue system requires a reformulation of the dialogue manager's basic assumptions behind, for example, user behavior and grounding strategies. But automatically detecting a sarcastic tone of voice is not a simple matter. This paper presents some experiments toward sarcasm recognition using prosodic, spectral, and contextual cues. Our results demonstrate that spectral and contextual features can be used to detect sarcasm as well as a human annotator would, and confirm a long-held claim in the field of psychology — that prosody alone is not sufficient to discern whether a speaker is being sarcastic.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The robust understanding of sarcasm in a spoken dialogue system requires a reformulation of the dialogue manager's basic assumptions behind, for example, user behavior and grounding strategies. But automatically detecting a sarcastic tone of voice is not a simple matter. This paper presents some experiments toward sarcasm recognition using prosodic, spectral, and contextual cues. Our results demonstrate that spectral and contextual features can be used to detect sarcasm as well as a human annotator would, and confirm a long-held claim in the field of psychology — that prosody alone is not sufficient to discern whether a speaker is being sarcastic.
Patel, Ronakkumar; Leuski, Anton; Traum, David
Dealing with Out of Domain Questions in Virtual Characters Proceedings Article
In: Proceedings of the 6th International Conference on Intelligent Virtual Agents, Marina del Rey, CA, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{patel_dealing_2006,
title = {Dealing with Out of Domain Questions in Virtual Characters},
author = {Ronakkumar Patel and Anton Leuski and David Traum},
url = {http://ict.usc.edu/pubs/Dealing%20with%20Out%20of%20Domain%20Questions%20in%20Virtual%20Characters.pdf},
year = {2006},
date = {2006-08-01},
booktitle = {Proceedings of the 6th International Conference on Intelligent Virtual Agents},
address = {Marina del Rey, CA},
abstract = {We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user?s interaction with the virtual character more natural and engaging.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user?s interaction with the virtual character more natural and engaging.
Roque, Antonio; Traum, David
An Information State-Based Dialogue Manager for Call for Fire Dialogues Proceedings Article
In: 7th SIGdial Workshop on Discourse and Dialogue, Sydney, Australia, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{roque_information_2006,
title = {An Information State-Based Dialogue Manager for Call for Fire Dialogues},
author = {Antonio Roque and David Traum},
url = {http://ict.usc.edu/pubs/An%20Information%20State-Based%20Dialogue%20Manager%20for%20Call%20for%20Fire%20Dialogues.pdf},
year = {2006},
date = {2006-07-01},
booktitle = {7th SIGdial Workshop on Discourse and Dialogue},
address = {Sydney, Australia},
abstract = {We present a dialogue manager for "Call for Fire" training dialogues. We describe the training environment, the domain, the features of its novel information state-based dialogue manager, the system it is a part of, and preliminary evaluation results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a dialogue manager for "Call for Fire" training dialogues. We describe the training environment, the domain, the features of its novel information state-based dialogue manager, the system it is a part of, and preliminary evaluation results.
Leuski, Anton; Patel, Ronakkumar; Traum, David; Kennedy, Brandon
Building Effective Question Answering Characters Proceedings Article
In: 7th SIGdial Workshop on Discourse and Dialogue, Sydney, Australia, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{leuski_building_2006,
title = {Building Effective Question Answering Characters},
author = {Anton Leuski and Ronakkumar Patel and David Traum and Brandon Kennedy},
url = {http://ict.usc.edu/pubs/Building%20Effective%20Question%20Answering%20Characters.pdf},
year = {2006},
date = {2006-07-01},
booktitle = {7th SIGdial Workshop on Discourse and Dialogue},
address = {Sydney, Australia},
abstract = {In this paper, we describe methods for building and evaluation of limited domain question-answering characters. Several classification techniques are tested, including text classification using support vector machines, language-model based retrieval, and cross-language information retrieval techniques, with the latter having the highest success rate. We also evaluated the effect of speech recognition errors on performance with users, finding that retrieval is robust until recognition reaches over 50% WER.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we describe methods for building and evaluation of limited domain question-answering characters. Several classification techniques are tested, including text classification using support vector machines, language-model based retrieval, and cross-language information retrieval techniques, with the latter having the highest success rate. We also evaluated the effect of speech recognition errors on performance with users, finding that retrieval is robust until recognition reaches over 50% WER.
Traum, David
Talking to Virtual Humans: Dialogue Models and Methodologies for Embodied Conversational Agents Book Section
In: Modeling Communication with Robots and Virtual Humans, pp. 296–309, 2006.
Abstract | Links | BibTeX | Tags:
@incollection{traum_talking_2006,
title = {Talking to Virtual Humans: Dialogue Models and Methodologies for Embodied Conversational Agents},
author = {David Traum},
url = {http://ict.usc.edu/pubs/Talking%20to%20Virtual%20Humans.pdf},
year = {2006},
date = {2006-04-01},
booktitle = {Modeling Communication with Robots and Virtual Humans},
pages = {296–309},
abstract = {Virtual Humans are artificial characters who look and act like humans, but inhabit a simulated environment. One important aspect of many virtual humans is their communicative dialogue ability. In this paper we outline a methodology for study of dialogue behavior and construction of virtual humans. We also consider three architectures for different types of virtual humans that have been built at the Institute for Creative Technologies.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Virtual Humans are artificial characters who look and act like humans, but inhabit a simulated environment. One important aspect of many virtual humans is their communicative dialogue ability. In this paper we outline a methodology for study of dialogue behavior and construction of virtual humans. We also consider three architectures for different types of virtual humans that have been built at the Institute for Creative Technologies.
Leuski, Anton; Pair, Jarrell; Traum, David; McNerney, Peter J.; Georgiou, Panayiotis G.; Patel, Ronakkumar
How to Talk to a Hologram Proceedings Article
In: Proceedings of the 11th International Conference on Intelligent User Interfaces, Sydney, Australia, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{leuski_how_2006,
title = {How to Talk to a Hologram},
author = {Anton Leuski and Jarrell Pair and David Traum and Peter J. McNerney and Panayiotis G. Georgiou and Ronakkumar Patel},
url = {http://ict.usc.edu/pubs/How%20to%20Talk%20to%20a%20Hologram.pdf},
year = {2006},
date = {2006-01-01},
booktitle = {Proceedings of the 11th International Conference on Intelligent User Interfaces},
address = {Sydney, Australia},
abstract = {There is a growing need for creating life-like virtual human simulations that can conduct a natural spoken dialog with a human student on a predefined subject. We present an overview of a spoken-dialog system that supports a person interacting with a full-size hologram-like virtual human character in an exhibition kiosk settings. We also give a brief summary of the natural language classification component of the system and describe the experiments we conducted with the system.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
There is a growing need for creating life-like virtual human simulations that can conduct a natural spoken dialog with a human student on a predefined subject. We present an overview of a spoken-dialog system that supports a person interacting with a full-size hologram-like virtual human character in an exhibition kiosk settings. We also give a brief summary of the natural language classification component of the system and describe the experiments we conducted with the system.
Dillenbourg, Pierre; Traum, David
Sharing Solutions: Persistence and Grounding in Multimodal Collaborative Problem Solving Journal Article
In: The Journal of the Learning Sciences, vol. 15, no. 1, pp. 121–151, 2006.
Abstract | Links | BibTeX | Tags:
@article{dillenbourg_sharing_2006,
title = {Sharing Solutions: Persistence and Grounding in Multimodal Collaborative Problem Solving},
author = {Pierre Dillenbourg and David Traum},
url = {http://ict.usc.edu/pubs/Sharing%20Solutions-%20Persistence%20and%20Grounding%20in%20Multimodal%20Collaborative%20Problem%20Solving.pdf},
year = {2006},
date = {2006-01-01},
journal = {The Journal of the Learning Sciences},
volume = {15},
number = {1},
pages = {121–151},
abstract = {This article reports on an exploratory study of the relationship between grounding and problem solving in multimodal computer-mediated collaboration. This article examines two different media, a shared whiteboard and a MOO environment that includes a text chat facility. A study was done on how the acknowledgment rate (how often partners give feedback of having perceived, understood, and accepted partner's contributions) varies according to the media and the content of interactions. It was expected that the whiteboard would serve to draw schemata that disambiguate chat utterances. Instead, results show that the whiteboard is primarily used to represent the state of problem solving and the chat is used for grounding information created on the whiteboard. These results are interpreted in terms of persistence: More persistent information is exchanged through the more persistent medium. The whiteboard was used as a shared memory rather than a grounding tool.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This article reports on an exploratory study of the relationship between grounding and problem solving in multimodal computer-mediated collaboration. This article examines two different media, a shared whiteboard and a MOO environment that includes a text chat facility. A study was done on how the acknowledgment rate (how often partners give feedback of having perceived, understood, and accepted partner's contributions) varies according to the media and the content of interactions. It was expected that the whiteboard would serve to draw schemata that disambiguate chat utterances. Instead, results show that the whiteboard is primarily used to represent the state of problem solving and the chat is used for grounding information created on the whiteboard. These results are interpreted in terms of persistence: More persistent information is exchanged through the more persistent medium. The whiteboard was used as a shared memory rather than a grounding tool.
Gandhe, Sudeep; Gordon, Andrew S.; Traum, David
Improving Question-Answering With Linking Dialogues Proceedings Article
In: International Conference on Intelligent User Interfaces (IUI-2006), Sydney, Australia, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{gandhe_improving_2006,
title = {Improving Question-Answering With Linking Dialogues},
author = {Sudeep Gandhe and Andrew S. Gordon and David Traum},
url = {http://ict.usc.edu/pubs/Improving%20Question-Answering%20With%20Linking%20Dialogues%20.pdf},
year = {2006},
date = {2006-01-01},
booktitle = {International Conference on Intelligent User Interfaces (IUI-2006)},
address = {Sydney, Australia},
abstract = {Question-answering dialogue systems have found many applications in interactive learning environments. This paper is concerned with one such application for Army leadership training, where trainees input free-text questions that elicit pre-recorded video responses. Since these responses are already crafted before the question is asked, a certain degree of incoherence exists between the question that is asked and the answer that is given. This paper explores the use of short linking dialogues that stand in between the question and its video response to alleviate the problem of incoherence. We describe a set of experiments with human generated linking dialogues that demonstrate their added value. We then describe our implementation of an automated method for utilizing linking dialogues and show that these have better coherence properties than the original system without linking dialogues.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Question-answering dialogue systems have found many applications in interactive learning environments. This paper is concerned with one such application for Army leadership training, where trainees input free-text questions that elicit pre-recorded video responses. Since these responses are already crafted before the question is asked, a certain degree of incoherence exists between the question that is asked and the answer that is given. This paper explores the use of short linking dialogues that stand in between the question and its video response to alleviate the problem of incoherence. We describe a set of experiments with human generated linking dialogues that demonstrate their added value. We then describe our implementation of an automated method for utilizing linking dialogues and show that these have better coherence properties than the original system without linking dialogues.
Swartout, William; Gratch, Jonathan; Hill, Randall W.; Hovy, Eduard; Lindheim, Richard; Marsella, Stacy C.; Rickel, Jeff; Traum, David
Simulation Meets Hollywood: Integrating Graphics, Sound, Story and Character for Immersive Simulation Book Section
In: Multimodal Intelligent Information Presentation, vol. 27, pp. 305–321, Springer, Netherlands, 2006.
Abstract | Links | BibTeX | Tags:
@incollection{swartout_simulation_2006,
title = {Simulation Meets Hollywood: Integrating Graphics, Sound, Story and Character for Immersive Simulation},
author = {William Swartout and Jonathan Gratch and Randall W. Hill and Eduard Hovy and Richard Lindheim and Stacy C. Marsella and Jeff Rickel and David Traum},
url = {http://ict.usc.edu/pubs/SIMULATION%20MEETS%20HOLLYWOOD-%20Integrating%20Graphics,%20Sound,%20Story%20and%20Character%20for%20Immersive%20Simulation.pdf},
year = {2006},
date = {2006-01-01},
booktitle = {Multimodal Intelligent Information Presentation},
volume = {27},
pages = {305–321},
publisher = {Springer},
address = {Netherlands},
abstract = {The Institute for Creative Technologies was created at the University of Southern California with the goal of bringing together researchers in simulation technology to collaborate with people from the entertainment industry. The idea was that much more compelling simulations could be developed if researchers who understood state-of-the-art simulation technology worked together with writers and directors who knew how to create compelling stories and characters. This paper presents our first major effort to realize that vision, the Mission Rehearsal Exercise Project, which confronts a soldier trainee with the kinds of dilemmas he might reasonably encounter in a peacekeeping operation. The trainee is immersed in a synthetic world and interacts with virtual humans: artificially intelligent and graphically embodied conversational agents that understand and generate natural language, reason about world events and respond appropriately to the trainee's actions or commands. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have also joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. In this paper we describe the Mission Rehearsal Exercise system and the insights gained through this large-scale integration.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The Institute for Creative Technologies was created at the University of Southern California with the goal of bringing together researchers in simulation technology to collaborate with people from the entertainment industry. The idea was that much more compelling simulations could be developed if researchers who understood state-of-the-art simulation technology worked together with writers and directors who knew how to create compelling stories and characters. This paper presents our first major effort to realize that vision, the Mission Rehearsal Exercise Project, which confronts a soldier trainee with the kinds of dilemmas he might reasonably encounter in a peacekeeping operation. The trainee is immersed in a synthetic world and interacts with virtual humans: artificially intelligent and graphically embodied conversational agents that understand and generate natural language, reason about world events and respond appropriately to the trainee's actions or commands. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have also joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. In this paper we describe the Mission Rehearsal Exercise system and the insights gained through this large-scale integration.
Roque, Antonio; Ai, Hua; Traum, David
Evaluation of an Information State-Based Dialogue Manager Proceedings Article
In: Brandial 2006: The 10th Workshop on the Semantics and Pragmatics of Dialogue, Potsdam, Germany, 2006.
Abstract | Links | BibTeX | Tags:
@inproceedings{roque_evaluation_2006,
title = {Evaluation of an Information State-Based Dialogue Manager},
author = {Antonio Roque and Hua Ai and David Traum},
url = {http://ict.usc.edu/pubs/Evaluation%20of%20an%20Information%20State-Based%20Dialogue%20Manager.pdf},
year = {2006},
date = {2006-01-01},
booktitle = {Brandial 2006: The 10th Workshop on the Semantics and Pragmatics of Dialogue},
address = {Potsdam, Germany},
abstract = {We describe an evaluation of an information state-based dialogue manager by measuring its accuracy in information state component updating.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We describe an evaluation of an information state-based dialogue manager by measuring its accuracy in information state component updating.
Swartout, William; Gratch, Jonathan; Hill, Randall W.; Hovy, Eduard; Marsella, Stacy C.; Rickel, Jeff; Traum, David
Toward Virtual Humans Journal Article
In: AI Magazine, 2006.
Abstract | Links | BibTeX | Tags:
@article{swartout_toward_2006,
title = {Toward Virtual Humans},
author = {William Swartout and Jonathan Gratch and Randall W. Hill and Eduard Hovy and Stacy C. Marsella and Jeff Rickel and David Traum},
url = {http://ict.usc.edu/pubs/Toward%20Virtual%20Humans.pdf},
year = {2006},
date = {2006-01-01},
journal = {AI Magazine},
abstract = {This paper describes the virtual humans developed as part of the Mission Rehearsal Exercise project, a virtual reality-based training system. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. We describe the key capabilities of the virtual humans, including task representation and reasoning, natural language dialogue, and emotion reasoning, and show how these capabilities are integrated to provide more human-level intelligence than would otherwise be possible.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper describes the virtual humans developed as part of the Mission Rehearsal Exercise project, a virtual reality-based training system. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. We describe the key capabilities of the virtual humans, including task representation and reasoning, natural language dialogue, and emotion reasoning, and show how these capabilities are integrated to provide more human-level intelligence than would otherwise be possible.
2005
Traum, David; Swartout, William; Marsella, Stacy C.; Gratch, Jonathan
Fight, Flight, or Negotiate: Believable Strategies for Conversing under Crisis Proceedings Article
In: 5th International Working Conference on Intelligent Virtual Agents, Kos, Greece, 2005.
Abstract | Links | BibTeX | Tags:
@inproceedings{traum_fight_2005,
title = {Fight, Flight, or Negotiate: Believable Strategies for Conversing under Crisis},
author = {David Traum and William Swartout and Stacy C. Marsella and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Fight,%20Flight,%20or%20Negotiate-%20Believable%20Strategies%20for%20Conversing%20under%20Crisis.pdf},
year = {2005},
date = {2005-09-01},
booktitle = {5th International Working Conference on Intelligent Virtual Agents},
address = {Kos, Greece},
abstract = {This paper des ribes a model of onversation strategies implemented in virtual humans designed to help people learn negotiation skills. We motivate and dis uss these strategies and their use to allow a virtual human to engage in omplex adversarial negotiation with a human trainee. Choi e of strategy depends on both the personality of the agent and assessment of the likelihood that the negotiation an be bene ial. Exe ution of strategies an be performed by hoosing spe i dialogue behaviors su h as whether and how to respond to a proposal. Current assessment of the value of the topi , the utility of the strategy, and aÆliation toward the other onversants an be used to dynami ally hange strategies throughout the ourse of a onversation. Examples will be given from the SASO-ST proje t, in whi h a trainee learns to negotiate by intera ting with virtual humans who employ these strategies.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper des ribes a model of onversation strategies implemented in virtual humans designed to help people learn negotiation skills. We motivate and dis uss these strategies and their use to allow a virtual human to engage in omplex adversarial negotiation with a human trainee. Choi e of strategy depends on both the personality of the agent and assessment of the likelihood that the negotiation an be bene ial. Exe ution of strategies an be performed by hoosing spe i dialogue behaviors su h as whether and how to respond to a proposal. Current assessment of the value of the topi , the utility of the strategy, and aÆliation toward the other onversants an be used to dynami ally hange strategies throughout the ourse of a onversation. Examples will be given from the SASO-ST proje t, in whi h a trainee learns to negotiate by intera ting with virtual humans who employ these strategies.
Traum, David; Swartout, William; Gratch, Jonathan; Marsella, Stacy C.; Kenny, Patrick G.; Hovy, Eduard; Narayanan, Shrikanth; Fast, Edward; Martinovski, Bilyana; Baghat, Rahul; Robinson, Susan; Marshall, Andrew; Wang, Dagen; Gandhe, Sudeep; Leuski, Anton
Dealing with Doctors: A Virtual Human for Non-team Interaction Proceedings Article
In: 6th SIGdial Conference on Discourse and Dialogue, Lisbon, Portugal, 2005.
Abstract | Links | BibTeX | Tags:
@inproceedings{traum_dealing_2005,
title = {Dealing with Doctors: A Virtual Human for Non-team Interaction},
author = {David Traum and William Swartout and Jonathan Gratch and Stacy C. Marsella and Patrick G. Kenny and Eduard Hovy and Shrikanth Narayanan and Edward Fast and Bilyana Martinovski and Rahul Baghat and Susan Robinson and Andrew Marshall and Dagen Wang and Sudeep Gandhe and Anton Leuski},
url = {http://ict.usc.edu/pubs/Dealing%20with%20Doctors.pdf},
year = {2005},
date = {2005-09-01},
booktitle = {6th SIGdial Conference on Discourse and Dialogue},
address = {Lisbon, Portugal},
abstract = {We present a virtual human do tor who an engage in multi-modal negotiation dialogue with people from other organizations. The do tor is part of the SASO-ST system, used for training for non-team intera tions},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a virtual human do tor who an engage in multi-modal negotiation dialogue with people from other organizations. The do tor is part of the SASO-ST system, used for training for non-team intera tions