Publications
Search
161.
Nouri, Elnaz; Traum, David
Generative Models of Cultural Decision Making for Virtual Agents Based on User’s Reported Values Proceedings Article
In: Intelligent Virtual Agents, pp. 310–315, Springer International Publishing, Boston, MA, 2014, ISBN: 978-3-319-09766-4.
@inproceedings{nouri_generative_2014,
title = {Generative Models of Cultural Decision Making for Virtual Agents Based on User’s Reported Values},
author = {Elnaz Nouri and David Traum},
url = {http://link.springer.com/chapter/10.1007/978-3-319-09767-1_39},
doi = {10.1007/978-3-319-09767-1_39},
isbn = {978-3-319-09766-4},
year = {2014},
date = {2014-08-01},
booktitle = {Intelligent Virtual Agents},
pages = {310–315},
publisher = {Springer International Publishing},
address = {Boston, MA},
series = {8637},
abstract = {Building computational models of cultural decision making for virtual agents based on behavioral data is a challenge because finding a reasonable mapping between the statistical data and the computational model is a difficult task. This paper shows how the weights on a multi attribute utility based decision making model can be set according to the values held by people elicited through a survey. If survey data from different cultures is available then this can be done to simulate cultural decision making behavior. We used the survey data of two sets of players from US and India playing the Dictator Game and the Ultimatum Game on-line. Analyzing their reported values in the survey enabled us to set up our model’s parameters based on their culture and simulate their behavior in the Ultimatum Game.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Building computational models of cultural decision making for virtual agents based on behavioral data is a challenge because finding a reasonable mapping between the statistical data and the computational model is a difficult task. This paper shows how the weights on a multi attribute utility based decision making model can be set according to the values held by people elicited through a survey. If survey data from different cultures is available then this can be done to simulate cultural decision making behavior. We used the survey data of two sets of players from US and India playing the Dictator Game and the Ultimatum Game on-line. Analyzing their reported values in the survey enabled us to set up our model’s parameters based on their culture and simulate their behavior in the Ultimatum Game.
162.
Chatterjee, Moitreya; Park, Sunghyun; Shim, Han Suk; Sagae, Kenji; Morency, Louis-Philippe
Verbal Behaviors and Persuasiveness in Online Multimedia Content Proceedings Article
In: Proceedings of the Second Workshop on Natural Language Processing for Social Media (SocialNLP), pp. 50, Dublin, Ireland, 2014.
@inproceedings{chatterjee_verbal_2014,
title = {Verbal Behaviors and Persuasiveness in Online Multimedia Content},
author = {Moitreya Chatterjee and Sunghyun Park and Han Suk Shim and Kenji Sagae and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/Verbal%20Behaviors%20and%20Persuasiveness%20in%20Online%20Multimedia%20Content.pdf},
year = {2014},
date = {2014-08-01},
booktitle = {Proceedings of the Second Workshop on Natural Language Processing for Social Media (SocialNLP)},
pages = {50},
address = {Dublin, Ireland},
abstract = {Persuasive communication is an essential component of our daily lives, whether it is negotiating, reviewing a product, or campaigning for the acceptance of a point of view. With the rapid expansion of social media websites such as YouTube, Vimeo and ExpoTV, it is becoming ever more important and useful to understand persuasiveness in social multimedia content. In this paper we present a novel analysis of verbal behavior, based on lexical usage and paraverbal markers of hesitation, in the context of predicting persuasiveness in online multi-media content. Toward the end goal of predicting perceived persuasion, this work also explores the potential differences in verbal behavior of people expressing a positive opinion (e.g., a positive movie review) versus a negative one. The analysis is performed on a multimedia corpus of 1,000 movie review videos annotated for persuasiveness. Our results show that verbal behavior can be a significant predictor of persuasiveness in such online multimedia content.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Persuasive communication is an essential component of our daily lives, whether it is negotiating, reviewing a product, or campaigning for the acceptance of a point of view. With the rapid expansion of social media websites such as YouTube, Vimeo and ExpoTV, it is becoming ever more important and useful to understand persuasiveness in social multimedia content. In this paper we present a novel analysis of verbal behavior, based on lexical usage and paraverbal markers of hesitation, in the context of predicting persuasiveness in online multi-media content. Toward the end goal of predicting perceived persuasion, this work also explores the potential differences in verbal behavior of people expressing a positive opinion (e.g., a positive movie review) versus a negative one. The analysis is performed on a multimedia corpus of 1,000 movie review videos annotated for persuasiveness. Our results show that verbal behavior can be a significant predictor of persuasiveness in such online multimedia content.
163.
Hartholt, Arno; Traum, David; Marsella, Stacy; Morency, Louis-Philippe; Shapiro, Ari; Gratch, Jonathan
A Shared, Modular Architecture for Developing Virtual Humans Proceedings Article
In: Proceedings of the Workshop on Architectures and Standards for Intelligent Virtual Agents at IVA 2014, pp. 4–7, Boston, MA, 2014.
@inproceedings{hartholt_shared_2014,
title = {A Shared, Modular Architecture for Developing Virtual Humans},
author = {Arno Hartholt and David Traum and Stacy Marsella and Louis-Philippe Morency and Ari Shapiro and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/A%20Shared%20Modular%20Architecture%20for%20Developing%20Virtual%20Humans.pdf},
doi = {10.2390/biecoll-wasiva2014-02},
year = {2014},
date = {2014-08-01},
booktitle = {Proceedings of the Workshop on Architectures and Standards for Intelligent Virtual Agents at IVA 2014},
pages = {4–7},
address = {Boston, MA},
abstract = {Realizing the full potential of intelligent virtual agents requires compelling characters that can engage users in meaningful and realistic social interactions, and an ability to develop these characters effectively and efficiently. Advances are needed in individual capabilities, but perhaps more importantly, fundamental questions remain as to how best to integrate these capabilities into a single framework that allows us to efficiently create characters that can engage users in meaningful and realistic social interactions. This integration requires in-depth, inter-disciplinary understanding few individuals, or even teams of individuals, possess.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Realizing the full potential of intelligent virtual agents requires compelling characters that can engage users in meaningful and realistic social interactions, and an ability to develop these characters effectively and efficiently. Advances are needed in individual capabilities, but perhaps more importantly, fundamental questions remain as to how best to integrate these capabilities into a single framework that allows us to efficiently create characters that can engage users in meaningful and realistic social interactions. This integration requires in-depth, inter-disciplinary understanding few individuals, or even teams of individuals, possess.
164.
Woo, Simon S.; Mirkovic, Jelena; Artstein, Ron; Kaiser, Elsi
Life-Experience Passwords (LEPs) Proceedings Article
In: Proceedings of the Symposium on Usable Privacy and Security (SOUPS), Menlo Park, CA, 2014.
@inproceedings{woo_life-experience_2014,
title = {Life-Experience Passwords (LEPs)},
author = {Simon S. Woo and Jelena Mirkovic and Ron Artstein and Elsi Kaiser},
url = {http://ict.usc.edu/pubs/Life-Experience%20Passwords%20(LEPs).pdf},
year = {2014},
date = {2014-07-01},
booktitle = {Proceedings of the Symposium on Usable Privacy and Security (SOUPS)},
address = {Menlo Park, CA},
abstract = {User-supplied textual passwords are extensively used today for user authentication. However, these passwords have serious de⬚ciencies in the way they interact with humans' natural ability to form memories. Strong passwords that are hard to crack are also often hard for humans to remember, while memorable passwords are easily brute-forced or guessed. We propose a novel password design textbackslashtextbackslashvphantom life-experience passwords (LEPs). We explain how to use users' existing episodic memories about de⬚ning life events to create memorable and hard-to-guess passwords and discuss challenges involved in design and use of LEPs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
User-supplied textual passwords are extensively used today for user authentication. However, these passwords have serious de⬚ciencies in the way they interact with humans' natural ability to form memories. Strong passwords that are hard to crack are also often hard for humans to remember, while memorable passwords are easily brute-forced or guessed. We propose a novel password design textbackslashtextbackslashvphantom life-experience passwords (LEPs). We explain how to use users' existing episodic memories about de⬚ning life events to create memorable and hard-to-guess passwords and discuss challenges involved in design and use of LEPs.
165.
DeVault, David; Stone, Matthew
Pursuing and Demonstrating Understanding in Dialogue Book Section
In: Natural Language Generation in Interactive Systems, pp. 34–62, Cambridge University Press, 2014.
@incollection{devault_pursuing_2014,
title = {Pursuing and Demonstrating Understanding in Dialogue},
author = {David DeVault and Matthew Stone},
url = {http://www.cs.rutgers.edu/ mdstone/pubs/dialogue11.pdf},
year = {2014},
date = {2014-07-01},
booktitle = {Natural Language Generation in Interactive Systems},
pages = {34–62},
publisher = {Cambridge University Press},
abstract = {The appeal of dialogue as an interface modality is its ability to support open-nded mixed-initiative interaction. Many systems o⬚er rich and extensive capabilities, but must support infrequent and untrained users. In such cases, it's unreasonable to expect users to know the actions they need in advance, or to be able to specify them using a regimented scheme of commands or menu options. Dialogue o⬚ers the potential for the user to talk through their needs with the system and arrive collaboratively at a feasible solution.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The appeal of dialogue as an interface modality is its ability to support open-nded mixed-initiative interaction. Many systems o⬚er rich and extensive capabilities, but must support infrequent and untrained users. In such cases, it's unreasonable to expect users to know the actions they need in advance, or to be able to specify them using a regimented scheme of commands or menu options. Dialogue o⬚ers the potential for the user to talk through their needs with the system and arrive collaboratively at a feasible solution.
166.
Rahimtoroghi, Elahe; Corcoran, Thomas; Swanson, Reid; Walker, Marilyn A.; Sagae, Kenji; Gordon, Andrew S.
Minimal Narrative Annotation Schemes and Their Applications Proceedings Article
In: Intelligent Narrative Technologies 7: Papers from the 2014 Workshop, Milwaukee, WI, 2014.
@inproceedings{rahimtoroghi_minimal_2014,
title = {Minimal Narrative Annotation Schemes and Their Applications},
author = {Elahe Rahimtoroghi and Thomas Corcoran and Reid Swanson and Marilyn A. Walker and Kenji Sagae and Andrew S. Gordon},
url = {http://ict.usc.edu/pubs/Minimal%20Narrative%20Annotation%20Schemes%20and%20Their%20Applications.PDF},
year = {2014},
date = {2014-06-01},
booktitle = {Intelligent Narrative Technologies 7: Papers from the 2014 Workshop},
address = {Milwaukee, WI},
abstract = {The increased use of large corpora in narrative research has created new opportunities for empirical research and intelligent narrative technologies. To best exploit the value of these corpora, several research groups are eschewing complex discourse analysis techniques in favor of high-level minimalist narrative annotation schemes that can be quickly applied, achieve high inter-rater agreement, and are amenable to automation using machine-learning techniques. In this paper we compare different annotation schemes that have been employed by two groups of researchers to annotate large corpora of narrative text. Using a dualannotation methodology, we investigate the correlation between narrative clauses distinguished by their structural role (orientation, action, evaluation), their subjectivity, and their narrative level within the discourse. We find that each simple narrative annotation scheme captures a structurally distinct characteristic of real-world narratives, and each combination of labels is evident in a corpus of 19 weblog narratives (951 narrative clauses). We discuss several potential applications of minimalist narrative annotation schemes, noting the combination of label across these two annotation schemes that best support each task.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The increased use of large corpora in narrative research has created new opportunities for empirical research and intelligent narrative technologies. To best exploit the value of these corpora, several research groups are eschewing complex discourse analysis techniques in favor of high-level minimalist narrative annotation schemes that can be quickly applied, achieve high inter-rater agreement, and are amenable to automation using machine-learning techniques. In this paper we compare different annotation schemes that have been employed by two groups of researchers to annotate large corpora of narrative text. Using a dualannotation methodology, we investigate the correlation between narrative clauses distinguished by their structural role (orientation, action, evaluation), their subjectivity, and their narrative level within the discourse. We find that each simple narrative annotation scheme captures a structurally distinct characteristic of real-world narratives, and each combination of labels is evident in a corpus of 19 weblog narratives (951 narrative clauses). We discuss several potential applications of minimalist narrative annotation schemes, noting the combination of label across these two annotation schemes that best support each task.
167.
Core, Mark; Lane, H. Chad; Traum, David
Intelligent Tutoring Support for Learners Interacting with Virtual Humans Book Section
In: Design Recommendations for Intelligent Tutoring Systems, vol. 2, pp. 249 – 257, 2014, ISBN: 978-0-9893923-2-7.
@incollection{core_intelligent_2014,
title = {Intelligent Tutoring Support for Learners Interacting with Virtual Humans},
author = {Mark Core and H. Chad Lane and David Traum},
url = {http://books.google.com/books?hl=en&lr=&id=BNWEBAAAQBAJ&oi=fnd&pg=PR2&dq=+Design+Recommendations+for+Intelligent+Tutoring+Systems,+volume+2&ots=jIk3zyGi4M&sig=qb_hc4KKE3-rMh2mrs8WkxBicG4#v=onepage&q&f=false},
isbn = {978-0-9893923-2-7},
year = {2014},
date = {2014-06-01},
booktitle = {Design Recommendations for Intelligent Tutoring Systems},
volume = {2},
pages = {249 – 257},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
168.
Morbini, Fabrizio; DeVault, David; Georgila, Kallirroi; Artstein, Ron; Traum, David; Morency, Louis-Philippe
A Demonstration of Dialogue Processing in SimSensei Kiosk Proceedings Article
In: 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 254, 2014.
@inproceedings{morbini_demonstration_2014,
title = {A Demonstration of Dialogue Processing in SimSensei Kiosk},
author = {Fabrizio Morbini and David DeVault and Kallirroi Georgila and Ron Artstein and David Traum and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/A%20Demonstration%20of%20Dialogue%20Processing%20in%20SimSensei%20Kiosk.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {15th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
pages = {254},
abstract = {This demonstration highlights the dialogue processing in SimSensei Kiosk, a virtual human dialogue system that con- ducts interviews related to psychological distress conditions such as depression, anxiety, and post-traumatic stress disorder (PTSD). The dialogue processing in SimSensei Kiosk allows the system to con- duct coherent spoken interviews of human users that are 15-25 minutes in length, and in which users feel comfortable talking and openly sharing information. We present the design of the individual dialogue components, and show examples of natural conversation flow between the sys- tem and users, including expressions of empathy, follow-up responses and continuation prompts, and turn-taking.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This demonstration highlights the dialogue processing in SimSensei Kiosk, a virtual human dialogue system that con- ducts interviews related to psychological distress conditions such as depression, anxiety, and post-traumatic stress disorder (PTSD). The dialogue processing in SimSensei Kiosk allows the system to con- duct coherent spoken interviews of human users that are 15-25 minutes in length, and in which users feel comfortable talking and openly sharing information. We present the design of the individual dialogue components, and show examples of natural conversation flow between the sys- tem and users, including expressions of empathy, follow-up responses and continuation prompts, and turn-taking.
169.
Nouri, Elnaz; Traum, David
Initiative Taking in Negotiation Proceedings Article
In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 186–193, 2014.
@inproceedings{nouri_initiative_2014,
title = {Initiative Taking in Negotiation},
author = {Elnaz Nouri and David Traum},
url = {http://ict.usc.edu/pubs/Initiative%20Taking%20in%20Negotiation.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)},
pages = {186–193},
abstract = {We examine the relationship between initiative behavior in negotiation dialogues and the goals and outcomes of the negotiation. We propose a novel annotation scheme for dialogue initiative, including four labels for initiative and response behavior in a dialogue turn. We annotate an existing human-human negotiation dataset, and use initiative-based features to try to predict both negotiation goal and outcome, comparing our results to prior work using other (non-initiative) features sets. Results show that combining initiative features with other features leads to improvements over either set and a majority class baseline.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We examine the relationship between initiative behavior in negotiation dialogues and the goals and outcomes of the negotiation. We propose a novel annotation scheme for dialogue initiative, including four labels for initiative and response behavior in a dialogue turn. We annotate an existing human-human negotiation dataset, and use initiative-based features to try to predict both negotiation goal and outcome, comparing our results to prior work using other (non-initiative) features sets. Results show that combining initiative features with other features leads to improvements over either set and a majority class baseline.
170.
Gandhe, Sudeep; Traum, David
SAWDUST: a Semi-Automated Wizard Dialogue Utterance Selection Tool for domain-independent large-domain dialogue Proceedings Article
In: SIGDIAL 2014 Conference, Association for Computational Linguistics, Philadelphia, PA, 2014.
@inproceedings{gandhe_sawdust_2014,
title = {SAWDUST: a Semi-Automated Wizard Dialogue Utterance Selection Tool for domain-independent large-domain dialogue},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/SAWDUST%20-%20a%20Semi-Automated%20Wizard%20Dialogue%20Utterance%20Selection%20Tool%20for%20domain-independent%20large-domain%20dialogue.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {SIGDIAL 2014 Conference},
publisher = {Association for Computational Linguistics},
address = {Philadelphia, PA},
abstract = {We present a tool that allows human wizards to select appropriate response utterances for a given dialogue context from a set of utterances observed in a dialogue corpus. Such a tool can be used in Wizard-of-Oz studies and for collecting data which can be used for training and/or evaluating automatic dialogue models. We also propose to incorporate such automatic dialogue models back into the tool as an aid in selecting utterances from a large dialogue corpus. The tool allows a user to rank candidate utterances for selection according to these automatic models.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a tool that allows human wizards to select appropriate response utterances for a given dialogue context from a set of utterances observed in a dialogue corpus. Such a tool can be used in Wizard-of-Oz studies and for collecting data which can be used for training and/or evaluating automatic dialogue models. We also propose to incorporate such automatic dialogue models back into the tool as an aid in selecting utterances from a large dialogue corpus. The tool allows a user to rank candidate utterances for selection according to these automatic models.
171.
Georgila, Kallirroi; Nelson, Claire; Traum, David
Single-agent vs. multi-agent techniques for concurrent reinforcement learning of negotiation dialogue policies Proceedings Article
In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 500–510, Association for Computational Linguistics, Baltimore, MD, 2014.
@inproceedings{georgila_single-agent_2014,
title = {Single-agent vs. multi-agent techniques for concurrent reinforcement learning of negotiation dialogue policies},
author = {Kallirroi Georgila and Claire Nelson and David Traum},
url = {https://www.aclweb.org/anthology/P/P14/P14-1047.xhtml},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
volume = {1},
pages = {500–510},
publisher = {Association for Computational Linguistics},
address = {Baltimore, MD},
abstract = {We use single-agent and multi-agent Reinforcement Learning (RL) for learning dialogue policies in a resource allocation negotiation scenario. Two agents learn concurrently by interacting with each other without any need for simulated users (SUs) to train against or corpora to learn from. In particular, we compare the Qlearning, Policy Hill-Climbing (PHC) and Win or Learn Fast Policy Hill-Climbing (PHC-WoLF) algorithms, varying the scenario complexity (state space size), the number of training episodes, the learning rate, and the exploration rate. Our results show that generally Q-learning fails to converge whereas PHC and PHC-WoLF always converge and perform similarly. We also show that very high gradually decreasing exploration rates are required for convergence. We conclude that multiagent RL of dialogue policies is a promising alternative to using single-agent RL and SUs or learning directly from corpora.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We use single-agent and multi-agent Reinforcement Learning (RL) for learning dialogue policies in a resource allocation negotiation scenario. Two agents learn concurrently by interacting with each other without any need for simulated users (SUs) to train against or corpora to learn from. In particular, we compare the Qlearning, Policy Hill-Climbing (PHC) and Win or Learn Fast Policy Hill-Climbing (PHC-WoLF) algorithms, varying the scenario complexity (state space size), the number of training episodes, the learning rate, and the exploration rate. Our results show that generally Q-learning fails to converge whereas PHC and PHC-WoLF always converge and perform similarly. We also show that very high gradually decreasing exploration rates are required for convergence. We conclude that multiagent RL of dialogue policies is a promising alternative to using single-agent RL and SUs or learning directly from corpora.
172.
Morbini, Fabrizio; Forbell, Eric; Sagae, Kenji
Improving Classification-Based Natural Language Understanding with Non-Expert Annotation Proceedings Article
In: Proceedings of SIGDIAL 2014, pp. 69–73, Philadelphia, PA, 2014.
@inproceedings{morbini_improving_2014,
title = {Improving Classification-Based Natural Language Understanding with Non-Expert Annotation},
author = {Fabrizio Morbini and Eric Forbell and Kenji Sagae},
url = {http://ict.usc.edu/pubs/Improved%20Classification-based%20Natural%20Language%20Understanding%20with%20Non-Expert%20Annotation.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of SIGDIAL 2014},
pages = {69–73},
address = {Philadelphia, PA},
abstract = {Although data-driven techniques are commonly used for Natural Language Understanding in dialogue systems, their efficacy is often hampered by the lack of appropriate annotated training data in sufficient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based language understanding in conversational dialogue systems. Experiments using a webaccessible conversational character that interacts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert annotation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Although data-driven techniques are commonly used for Natural Language Understanding in dialogue systems, their efficacy is often hampered by the lack of appropriate annotated training data in sufficient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based language understanding in conversational dialogue systems. Experiments using a webaccessible conversational character that interacts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert annotation.
173.
Gratch, Jonathan; Artstein, Ron; Lucas, Gale; Stratou, Giota; Scherer, Stefan; Nazarian, Angela; Wood, Rachel; Boberg, Jill; DeVault, David; Marsella, Stacy; Traum, David; Rizzo, Albert; Morency, Louis-Philippe
The Distress Analysis Interview Corpus of human and computer interviews Proceedings Article
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 3123–3128, LREC, Reykjavik, Iceland, 2014.
@inproceedings{gratch_distress_2014,
title = {The Distress Analysis Interview Corpus of human and computer interviews},
author = {Jonathan Gratch and Ron Artstein and Gale Lucas and Giota Stratou and Stefan Scherer and Angela Nazarian and Rachel Wood and Jill Boberg and David DeVault and Stacy Marsella and David Traum and Albert Rizzo and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/The%20Distress%20Analysis%20Interview%20Corpus%20of%20human%20and%20computer%20interviews.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014)},
pages = {3123–3128},
publisher = {LREC},
address = {Reykjavik, Iceland},
abstract = {The Distress Analysis Interview Corpus (DAIC) contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post traumatic stress disorder. The interviews are conducted by humans, human controlled agents and autonomous agents, and the participants include both distressed and non-distressed individuals. Data collected include audio and video recordings and extensive questionnaire responses; parts of the corpus have been transcribed and annotated for a variety of verbal and non-verbal features. The corpus has been used to support the creation of an automated interviewer agent, and for research on the automatic identification of psychological distress.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Distress Analysis Interview Corpus (DAIC) contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post traumatic stress disorder. The interviews are conducted by humans, human controlled agents and autonomous agents, and the participants include both distressed and non-distressed individuals. Data collected include audio and video recordings and extensive questionnaire responses; parts of the corpus have been transcribed and annotated for a variety of verbal and non-verbal features. The corpus has been used to support the creation of an automated interviewer agent, and for research on the automatic identification of psychological distress.
174.
DeVault, David; Artstein, Ron; Benn, Grace; Dey, Teresa; Fast, Edward; Gainer, Alesia; Georgila, Kallirroi; Gratch, Jonathan; Hartholt, Arno; Lhommet, Margaux; Lucas, Gale; Marsella, Stacy C.; Fabrizio, Morbini; Nazarian, Angela; Scherer, Stefan; Stratou, Giota; Suri, Apar; Traum, David; Wood, Rachel; Xu, Yuyu; Rizzo, Albert; Morency, Louis-Philippe
SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support Proceedings Article
In: Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), pp. 1061–1068, International Foundation for Autonomous Agents and Multiagent Systems, Paris, France, 2014.
@inproceedings{devault_simsensei_2014,
title = {SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support},
author = {David DeVault and Ron Artstein and Grace Benn and Teresa Dey and Edward Fast and Alesia Gainer and Kallirroi Georgila and Jonathan Gratch and Arno Hartholt and Margaux Lhommet and Gale Lucas and Stacy C. Marsella and Morbini Fabrizio and Angela Nazarian and Stefan Scherer and Giota Stratou and Apar Suri and David Traum and Rachel Wood and Yuyu Xu and Albert Rizzo and Louis-Philippe Morency},
url = {https://dl.acm.org/citation.cfm?id=2617415},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)},
pages = {1061–1068},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Paris, France},
abstract = {We present SimSensei Kiosk, an implemented virtual human interviewer designed to create an engaging face-to-face inter-action where the user feels comfortable talking and sharing information. SimSensei Kiosk is also designed to create in- teractional situations favorable to the automatic assessment of distress indicators, de_ned as verbal and nonverbal behav- iors correlated with depression, anxiety or post-traumatic stress disorder (PTSD). In this paper, we summarize the de- sign methodology, performed over the past two years, which is based on three main development cycles: (1) analysis of face-to-face human interactions to identify potential distress indicators, dialogue policies and virtual human gestures, (2) development and analysis of a Wizard-of-Oz prototype sys- tem where two human operators were deciding the spoken and gestural responses, and (3) development of a fully au- tomatic virtual interviewer able to engage users in 15-25 minute interactions. We show the potential of our fully auto- matic virtual human interviewer in a user study, and situate its performance in relation to the Wizard-of-Oz prototype.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present SimSensei Kiosk, an implemented virtual human interviewer designed to create an engaging face-to-face inter-action where the user feels comfortable talking and sharing information. SimSensei Kiosk is also designed to create in- teractional situations favorable to the automatic assessment of distress indicators, de_ned as verbal and nonverbal behav- iors correlated with depression, anxiety or post-traumatic stress disorder (PTSD). In this paper, we summarize the de- sign methodology, performed over the past two years, which is based on three main development cycles: (1) analysis of face-to-face human interactions to identify potential distress indicators, dialogue policies and virtual human gestures, (2) development and analysis of a Wizard-of-Oz prototype sys- tem where two human operators were deciding the spoken and gestural responses, and (3) development of a fully au- tomatic virtual interviewer able to engage users in 15-25 minute interactions. We show the potential of our fully auto- matic virtual human interviewer in a user study, and situate its performance in relation to the Wizard-of-Oz prototype.
175.
Visser, Thomas; Traum, David; DeVault, David; Akker, Rieks
A model for incremental grounding in spoken dialogue systems Journal Article
In: Journal on Multimodal User Interfaces, vol. 8, no. 1, pp. 61–73, 2014, ISSN: 1783-7677, 1783-8738.
@article{visser_model_2014,
title = {A model for incremental grounding in spoken dialogue systems},
author = {Thomas Visser and David Traum and David DeVault and Rieks Akker},
url = {http://ict.usc.edu/pubs/A%20Model%20for%20Incremental%20Grounding%20in%20Spoken%20Dialogue%20Systems.pdf},
doi = {10.1007/s12193-013-0147-7},
issn = {1783-7677, 1783-8738},
year = {2014},
date = {2014-03-01},
journal = {Journal on Multimodal User Interfaces},
volume = {8},
number = {1},
pages = {61–73},
abstract = {We present a computational model of incremental grounding, including state updates and action selection. The model is inspired by corpus-based examples of overlapping utterances of several sorts, including backchannels and completions. The model has also been partially implemented within a virtual human system that includes incremental understanding, and can be used to track grounding and provide overlapping verbal and non-verbal behaviors from a listener, before a speaker has completed her utterance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We present a computational model of incremental grounding, including state updates and action selection. The model is inspired by corpus-based examples of overlapping utterances of several sorts, including backchannels and completions. The model has also been partially implemented within a virtual human system that includes incremental understanding, and can be used to track grounding and provide overlapping verbal and non-verbal behaviors from a listener, before a speaker has completed her utterance.
176.
Artstein, Ron; Smith, Stephen; Traum, David; Alexander, Oleg; Leuski, Anton; Jones, Andrew; Georgila, Kallirroi; Debevec, Paul; Swartout, William; Maio, Heather
Time-offset Interaction with a Holocaust Survivor Proceedings Article
In: Proceedings of IUI 2014, pp. 163–168, ACM Press, Haifa, Israel, 2014, ISBN: 978-1-4503-2184-6.
@inproceedings{artstein_time-offset_2014,
title = {Time-offset Interaction with a Holocaust Survivor},
author = {Ron Artstein and Stephen Smith and David Traum and Oleg Alexander and Anton Leuski and Andrew Jones and Kallirroi Georgila and Paul Debevec and William Swartout and Heather Maio},
url = {http://ict.usc.edu/pubs/Time-Offset%20Interaction%20with%20a%20Holocaust%20Survivor.pdf},
doi = {10.1145/2557500.2557540},
isbn = {978-1-4503-2184-6},
year = {2014},
date = {2014-02-01},
booktitle = {Proceedings of IUI 2014},
pages = {163–168},
publisher = {ACM Press},
address = {Haifa, Israel},
abstract = {Time-offset interaction is a new technology that allows for two-way communication with a person who is not available for conversation in real time: a large set of statements are prepared in advance, and users access these statements through natural conversation that mimics face-to-face interaction. Conversational reactions to user questions are retrieved through a statistical classifier, using technology that is similar to previous interactive systems with synthetic characters; however, all of the retrieved utterances are genuine statements by a real person. Recordings of answers, listening and idle behaviors, and blending techniques are used to create a persistent visual image of the person throughout the interaction. A proof-of-concept has been implemented using the likeness of Pinchas Gutter, a Holocaust survivor, enabling short conversations about his family, his religious views, and resistance. This proof-of-concept has been shown to dozens of people, from school children to Holocaust scholars, with many commenting on the impact of the experience and potential for this kind of interface.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Time-offset interaction is a new technology that allows for two-way communication with a person who is not available for conversation in real time: a large set of statements are prepared in advance, and users access these statements through natural conversation that mimics face-to-face interaction. Conversational reactions to user questions are retrieved through a statistical classifier, using technology that is similar to previous interactive systems with synthetic characters; however, all of the retrieved utterances are genuine statements by a real person. Recordings of answers, listening and idle behaviors, and blending techniques are used to create a persistent visual image of the person throughout the interaction. A proof-of-concept has been implemented using the likeness of Pinchas Gutter, a Holocaust survivor, enabling short conversations about his family, his religious views, and resistance. This proof-of-concept has been shown to dozens of people, from school children to Holocaust scholars, with many commenting on the impact of the experience and potential for this kind of interface.
177.
Leuski, Anton; Gowrisankar, Rasiga; Richmond, Todd; Shapiro, Ari; Xu, Yuyu; Feng, Andrew
Mobile Personal Healthcare Mediated by Virtual Humans Proceedings Article
In: Proceedings of the companion publication of the 19th international conference on Intelligent User Interfaces, pp. 21–24, ACM Press, Haifa, Israel, 2014, ISBN: 978-1-4503-2729-9.
@inproceedings{leuski_mobile_2014,
title = {Mobile Personal Healthcare Mediated by Virtual Humans},
author = {Anton Leuski and Rasiga Gowrisankar and Todd Richmond and Ari Shapiro and Yuyu Xu and Andrew Feng},
url = {http://dl.acm.org/citation.cfm?doid=2559184.2559200},
doi = {10.1145/2559184.2559200},
isbn = {978-1-4503-2729-9},
year = {2014},
date = {2014-02-01},
booktitle = {Proceedings of the companion publication of the 19th international conference on Intelligent User Interfaces},
pages = {21–24},
publisher = {ACM Press},
address = {Haifa, Israel},
abstract = {We demonstrate Ally—-a prototype interface for a consumer–level medical diagnostic device. It is an interactive virtual character—-Virtual Human (VH)—-that listens to user's concern, collects and processes sensor data, offers advice, guides the user through a self-administered medical tests, and answers the user's questions. The primary focus of this demo is on the VH, we describe and demonstrate the technologies for language analysis, dialogue management, response generation and presentation. The sensing and medical decision making components are simulated in the current system, but possible applications and extensions are discussed.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We demonstrate Ally—-a prototype interface for a consumer–level medical diagnostic device. It is an interactive virtual character—-Virtual Human (VH)—-that listens to user's concern, collects and processes sensor data, offers advice, guides the user through a self-administered medical tests, and answers the user's questions. The primary focus of this demo is on the VH, we describe and demonstrate the technologies for language analysis, dialogue management, response generation and presentation. The sensing and medical decision making components are simulated in the current system, but possible applications and extensions are discussed.
178.
Nouri, Elnaz; Traum, David
Cultural Differences in Playing Repeated Ultimatum Game online with Virtual Humans Proceedings Article
In: The 47 Annual Hawaii International Conference on System Sciences, pp. 1213–1220, Computer Society Press, Big Island of Hawaii, 2014.
@inproceedings{nouri_cultural_2014,
title = {Cultural Differences in Playing Repeated Ultimatum Game online with Virtual Humans},
author = {Elnaz Nouri and David Traum},
url = {http://ict.usc.edu/pubs/Cultural%20Differences%20in%20Playing%20Repeated%20Ultimatum%20Game%20Online%20with%20Virtual%20Humans.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {The 47 Annual Hawaii International Conference on System Sciences},
pages = {1213–1220},
publisher = {Computer Society Press},
address = {Big Island of Hawaii},
abstract = {Efficient interaction between computational agents and users in tasks such as negotiation and bargaining requires recognition and understanding of potential differences in human behavior. Cultural differences in humans bargaining behavior are the focus of this study. We investigate the dynamics of human game playing with a conversational computational agent (Virtual Human). We demonstrate that the cultural background influences their observed behavior in this task. We investigate whether the social values held by the participants from each culture can at least partially explain the observed differences in behavior. We show that it is possible to automatically identify players’ cultures from their game behavior and to predict their upcoming decisions in different stages of a repeated game. We employ data collected from US and Indian participants playing repeated rounds of the Ultimatum Game online against a virtual human when low stakes are involved. Our results are comparable to the reported results of similar games played among people in laboratory conditions and with high stakes. The two cultures are different in terms of the statistics and the sequence of offers made in the game and their reported values. The findings of this study are valuable for development of culturally-sensitive computational agents for negotiation and bargaining.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Efficient interaction between computational agents and users in tasks such as negotiation and bargaining requires recognition and understanding of potential differences in human behavior. Cultural differences in humans bargaining behavior are the focus of this study. We investigate the dynamics of human game playing with a conversational computational agent (Virtual Human). We demonstrate that the cultural background influences their observed behavior in this task. We investigate whether the social values held by the participants from each culture can at least partially explain the observed differences in behavior. We show that it is possible to automatically identify players’ cultures from their game behavior and to predict their upcoming decisions in different stages of a repeated game. We employ data collected from US and Indian participants playing repeated rounds of the Ultimatum Game online against a virtual human when low stakes are involved. Our results are comparable to the reported results of similar games played among people in laboratory conditions and with high stakes. The two cultures are different in terms of the statistics and the sequence of offers made in the game and their reported values. The findings of this study are valuable for development of culturally-sensitive computational agents for negotiation and bargaining.
179.
Gandhe, Sudeep; Traum, David
A semi-automated evaluation metric for dialogue model coherence Proceedings Article
In: Fifth International Workshop on Spoken Dialogue systems, pp. 141–150, 2014.
@inproceedings{gandhe_semi-automated_2014,
title = {A semi-automated evaluation metric for dialogue model coherence},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/A%20semi-automated%20evaluation%20metric%20for%20dialogue%20model%20coherence.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Fifth International Workshop on Spoken Dialogue systems},
pages = {141–150},
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 = {inproceedings}
}
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.
180.
Yu, Zhou; Scherer, Stefen; Devault, David; Gratch, Jonathan; Stratou, Giota; Morency, Louis-Philippe; Cassell, Justine
Multimodal Prediction of Psychological Disorders: Learning Verbal and Nonverbal Commonalities in Adjacency Pairs Proceedings Article
In: Semdial 2013 DialDam: Proceedings of the 17th Workshop on the Semantics and Pragmatics of Dialogue, pp. 160–169, Amsterdam, The Netherlands, 2013.
@inproceedings{yu_multimodal_2013,
title = {Multimodal Prediction of Psychological Disorders: Learning Verbal and Nonverbal Commonalities in Adjacency Pairs},
author = {Zhou Yu and Stefen Scherer and David Devault and Jonathan Gratch and Giota Stratou and Louis-Philippe Morency and Justine Cassell},
url = {http://www.cs.cmu.edu/afs/cs/user/zhouyu/www/semdial_2013_zhou.pdf},
year = {2013},
date = {2013-12-01},
booktitle = {Semdial 2013 DialDam: Proceedings of the 17th Workshop on the Semantics and Pragmatics of Dialogue},
pages = {160–169},
address = {Amsterdam, The Netherlands},
abstract = {Semi-structured interviews are widely used in medical settings to gather information from individuals about psychological disorders, such as depression or anxiety. These interviews typically consist of a series of question and response pairs, which we refer to as adjacency pairs. We pro-pose a computational model, the Multi-modal HCRF, that considers the commonalities among adjacency pairs and information from multiple modalities to infer the psychological states of the interviewees. We collect data and perform experiments on a human to virtual human interaction data set. Our multimodal approach gives a significant advantage over conventional holistic approaches which ignore the adjacency pair context in predicting depression from semi-structured inter- views.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Semi-structured interviews are widely used in medical settings to gather information from individuals about psychological disorders, such as depression or anxiety. These interviews typically consist of a series of question and response pairs, which we refer to as adjacency pairs. We pro-pose a computational model, the Multi-modal HCRF, that considers the commonalities among adjacency pairs and information from multiple modalities to infer the psychological states of the interviewees. We collect data and perform experiments on a human to virtual human interaction data set. Our multimodal approach gives a significant advantage over conventional holistic approaches which ignore the adjacency pair context in predicting depression from semi-structured inter- views.
Filter
Sorry, no publications matched your criteria.