@inproceedings{artstein_listen_2017,

title = {Listen to My Body: Does Making Friends Help Influence People?},

author = {Ron Artstein and David Traum and Jill Boberg and Alesia Gainer and Jonathan Gratch and Emmanuel Johnson and Anton Leuski and Mikio Nakano},

url = {https://aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/view/15501/14979},

year  = {2017},

date = {2017-05-01},

booktitle = {Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference (FLAIRS-30)},

publisher = {AAAI},

address = {Marco Island, Florida},

abstract = {We investigate the effect of relational dialogue on creating rapport and exerting social influence in human-robot conversation, by comparing interactions with and without a relational component, and with different agent types. Human participants interact with two agents – a Nao robot and a virtual human – in four dialogue scenarios: one involving building familiarity, and three involving sharing information and persuasion in item-ranking tasks. Results show that both agents influence human decision-making; people prefer interacting with the robot, feel higher rapport with the robot, and believe the robot has more influence; and that objective influence of the agent on the person is increased by building familiarity, but is not significantly different between the agents.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{johnson_towards_2017,

title = {Towards An Autonomous Agent that Provides Automated Feedback on Students' Negotiation Skills},

author = {Emmanuel Johnson and Jonathan Gratch and David DeVault},

url = {http://dl.acm.org/citation.cfm?id=3091187},

year  = {2017},

date = {2017-05-01},

booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems},

pages = {410–418},

publisher = {International Foundation for Autonomous Agents and Multiagent Systems},

address = {Sao Paulo, Brazil},

abstract = {Although negotiation is an integral part of daily life, most people are unskilled negotiators. To improve one's skill set, a range of costly options including self-study guides, courses, and training programs are o ered by various companies and educational institutions. For those who can't a ord costly training options, virtual role playing agents o er a low-costalternative. To be e ective, these systems must allow students to engage in experiential learning exercises and provide personalized feedback on the learner's performance. In this paper, we show how a number of negotiation principles can be formalized and quanti ed. We then establish the pedagogical relevance of several automatic metrics, and show that these metrics are signi cantly correlated with negotiation outcomes in a human-agent negotiation. This illustrates the realism and helps to validate these principles. It also shows the potential of technology being used to quantify feedback that is traditionally provided through more qualitative approaches. The metrics we describe can provide students with personalized feedback on the errors they make in a negotiation exercise and thereby support guided experiential learning.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manini_physiological_2017,

title = {Physiological and behavioral correlates of babies’ social engagement with robot and virtual human artificial intelligence agents},

author = {Barbara Manini and Katherine Tsui and Adam Stone and Brian Scassellati and David Traum and Arcangelo Merla and Laura Ann Petitto},

url = {https://www.researchgate.net/publication/316167858_Physiological_and_behavioral_correlates_of_babies'_social_engagement_with_robot_and_virtual_human_artificial_intelligence_agents},

year  = {2017},

date = {2017-04-01},

booktitle = {Proceedings of SRCD},

address = {Austin, TX},

abstract = {Exposure to the patterns of natural language in early life—especially in ways that are rich in socially contingent interaction and conversation—is among the most powerful facilitators of the human language acquisition process (Petitto et al., 2016). Adults’ infant-directed language (e.g., simple rhythmic nursery rhymes), communicated in social interactions with joint attention, supports babies’ biological predisposition to language development in the first year of life (Brook & Meltzoff, 2015). Yet many babies have minimal language exposure in early life that can have devastating consequences for their language learning and reading success—such as the deaf baby. With the aim to develop a learning tool for babies deprived of natural language input during sensitive periods in human development, we studied whether artificial intelligent agents (social robots and virtual humans) can serve as an augmentative communicative partner in early infancy. Using innovative thermal IR imaging technology, we recorded, imaged, and analyzed infants’ emotional arousal and behavioral responses during social interactions with a robot and virtual human, as compared with a real human. We asked whether babies’ physiological and behavioral responses of joint attention during these robot and virtual human interactions were similar to or different from interactions with a real human. We hypothesized that if babyartificial agent emotional arousal measures were observed to be similar to humans, then artificial agents may potentially serve as a promising tool in facilitating language learning in infants with early-life minimal language exposure. Methods: 10 hearing (nonsigning) infants (five 6-9mths; five 9-12mths). Following Meltzoff et al. (2010), after a brief familiarization period with the robot, infants participated in 6 10 episodes of robot head and eye gaze turning (left or right). Two screens were placed on each side of the robot, rendering it “looking at the screen” when it turned its head. Contiguous with the robot’s gaze/head, both screens showed a nursery rhyme in ASL, performed alternatively by a virtual human or a real human (held constant: physical features and linguistic content). Results: Time-locked/integrated infant behavior and thermal responses were analyzed (c.f., Merla, 2004; Manini et al., 2013). (1) Behavioral data showed babies followed robot gaze, yet the Thermal IR data added new insights: Significant increase in nasal-tip temperature was observed, indicative of suppression of the sympathetic activity and increase of parasympathetic/pro-social attentiveness. (2) Thermal responses with virtual human vs real human revealed a phasic decrease of temperature likely associated with increased vigilance and higher cognitive attention processes (e.g., match-mismatch analysis). Discussion: Robots and virtual humans may be effective as augmentative communicative partners for young babies. Novel here, we observed an integrated physiological and behavioral response of joint attention and social engagement during babies’ interaction with the robot. Moreover, the virtual human elicited a peaked attentional arousal reaction, which may be indicative of linguistic stimuli detection and/or a “readiness to learn.” The integration of physiological and behavioral responses provide insights that pave the way for groundbreaking applications in the field of artificial intelligence (Merla, 2014) and augmentative learning tools that promote language acquisition in young children.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{woo_life-experience_2016,

title = {Life-experience passwords (LEPs)},

author = {Simon Woo and Elsi Kaiser and Ron Artstein and Jelena Mirkovic},

url = {http://dl.acm.org/citation.cfm?doid=2991079.2991107},

doi = {10.1145/2991079.2991107},

isbn = {978-1-4503-4771-6},

year  = {2016},

date = {2016-12-01},

booktitle = {Proceedings of the 32nd Annual Conference on Computer Security Applications},

pages = {113–126},

publisher = {ACM Press},

address = {Los Angeles, CA},

abstract = {Passwords are widely used for user authentication, but they are often difficult for a user to recall, easily cracked by automated programs and heavily reused. Security questions are also used for secondary authentication. They are more memorable than passwords, but are very easily guessed. We propose a new authentication mechanism, called "life-experience passwords (LEPs)," which outperforms passwords and security questions, both at recall and at security. Each LEP consists of several facts about a user-chosen past experience, such as a trip, a graduation, a wedding, etc. At LEP creation, the system extracts these facts from the user's input and transforms them into questions and answers. At authentication, the system prompts the user with questions and matches her answers with the stored ones. In this paper we propose two LEP designs, and evaluate them via user studies. We further compare LEPs to passwords, and find that: (1) LEPs are 30–47 bits stronger than an ideal, randomized, 8-character password, (2) LEPs are up to 3x more memorable, and (3) LEPs are reused half as often as passwords. While both LEPs and security questions use personal experiences for authentication, LEPs use several questions, which are closely tailored to each user. This increases LEP security against guessing attacks. In our evaluation, only 0.7% of LEPs were guessed by friends, while prior research found that friends could guess 17–25% of security questions. LEPs also contained a very small amount of sensitive or fake information. All these qualities make LEPs a promising, new authentication approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{core_learning_2016,

title = {Learning, Adaptive Support, Student Traits, and Engagement in Scenario-Based Learning},

author = {Mark G. Core and Kallirroi Georgila and Benjamin D. Nye and Daniel Auerbach and Zhi Fei Liu and Richard DiNinni},

url = {http://www.iitsecdocs.com/search},

year  = {2016},

date = {2016-11-01},

booktitle = {Proceedings from the Interservice/Industry Training, Simulation and Education Conference (I/ITSEC) 2016},

publisher = {National Training and Simulation Association},

address = {Orlando, FL},

abstract = {Scenario-based training systems pose an especially difficult challenge for an intelligent tutoring system (ITS). In addition to the basic problems of deciding when to intervene and what guidance to provide, the ITS must decide whether to give guidance directly (e.g., a hint message), indirectly through positive/negative results in the scenario, or to delay guidance until a post-scenario review session. There are a number of factors that an adaptive ITS should consider and we use self-report survey instruments to investigate the relationship between traits, learning strategies, expectations, learner behaviors derived from log files, post-use perceptions of the system, and pre-test and post-test results. We use the ELITE Lite Counseling training system as a testbed for our experiments. This system uses virtual role players to allow learners to practice leadership counseling skills, and is in use at the United States Military Academy (USMA). This paper analyzes two data sets. We collected data from local university students, a non-military population of roughly the same age as USMA Cadets using the system. For these local participants, we could administer surveys and pre-tests and post-tests, and collect log files recording clicks made while using ELITE Lite. The second data set comes from USMA itself but is limited to log files. In both populations, the ITS’s hints are effective at boosting scenario performance, and for the university students, the overall experience promoted learning, and survey results suggest that higher levels of organization in study habits may lead to greater learning with ELITE Lite. For the USMA Cadets, ELITE Lite is part of their Military Leadership course rather than an experiment, which could explain why we found higher scenario performance on average than the non-military population, and more use of the post-scenario review feature.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_niki_2016,

title = {Niki and Julie: A Robot and Virtual Human for Studying Multimodal Social Interaction},

author = {Ron Artstein and David Traum and Jill Boberg and Alesia Gainer and Jonathan Gratch and Emmanuel Johnson and Anton Leuski and Mikio Nakano},

url = {http://dl.acm.org/citation.cfm?doid=2993148.2998532},

doi = {10.1145/2993148.2998532},

isbn = {978-1-4503-4556-9},

year  = {2016},

date = {2016-11-01},

booktitle = {Proceedings of the 18th ACM International Conference on Multimodal Interaction},

pages = {402–403},

publisher = {ACM Press},

address = {Tokyo, Japan},

abstract = {We demonstrate two agents, a robot and a virtual human, which can be used for studying factors that impact social influence. The agents engage in dialogue scenarios that build familiarity, share information, and attempt to influence a human participant. The scenarios are variants of the classical “survival task,” where members of a team rank the importance of a number of items (e.g., items that might help one survive a crash in the desert). These are ranked individually and then re-ranked following a team discussion, and the difference in ranking provides an objective measure of social influence. Survival tasks have been used in psychology, virtual human research, and human-robot interaction. Our agents are operated in a “Wizard-of-Oz” fashion, where a hidden human operator chooses the agents’ dialogue actions while interacting with an experiment participant.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ravi_language_2016,

title = {Language Portability for Dialogue Systems: Translating a Question-Answering System from English into Tamil},

author = {Satheesh Ravi and Ron Artstein},

url = {http://www.aclweb.org/anthology/W16-3614},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of the SIGDIAL 2016 Conference},

pages = {111–116},

publisher = {Association for Computational Linguistics},

address = {Los Angeles, CA},

abstract = {A training and test set for a dialogue system in the form of linked questions and responses is translated from English into Tamil. Accuracy of identifying an appropriate response in Tamil is 79%, compared to the English accuracy of 89%, suggesting that translation can be useful to start up a dialogue system. Machine translation of Tamil inputs into English also results in 79% accuracy. However, machine translation of the English training data into Tamil results in a drop in accuracy to 54% when tested on manually authored Tamil, indicating that there is still a large gap before machine translated dialogue systems can interact with human users.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manuvinakurike_toward_2016,

title = {Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems},

author = {Ramesh Manuvinakurike and Maike Paetzel and Cheng Qu and David Schlangen and David DeVault},

url = {http://www.aclweb.org/anthology/W16-3632},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue},

pages = {252–262},

publisher = {Association for Computational Linguistics},

address = {Los Angeles, CA},

abstract = {In this paper, we present and evaluate an approach to incremental dialogue act (DA) segmentation and classification. Our approach utilizes prosodic, lexico-syntactic and contextual features, and achieves an encouraging level of performance in offline corpus-based evaluation as well as in simulated human-agent dialogues. Our approach uses a pipeline of sequential processing steps, and we investigate the contribution of different processing steps to DA segmentation errors. We present our results using both existing and new metrics for DA segmentation. The incremental DA segmentation capability described here may help future systems to allow more natural speech from users and enable more natural patterns of interaction.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manuvinakurike_real-time_2016,

title = {Real-Time Understanding of Complex Discriminative Scene Descriptions},

author = {Ramesh Manuvinakurike and Casey Kennington and David DeVault and David Schlangen},

url = {http://www.aclweb.org/anthology/W16-3630},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue},

pages = {232–241},

publisher = {Association for Computational Linguistics},

address = {Los Angeles, CA},

abstract = {Real-world scenes typically have complex structure, and utterances about them consequently do as well. We devise and evaluate a model that processes descriptions of complex configurations of geometric shapes and can identify the described scenes among a set of candidates, including similar distractors. The model works with raw images of scenes, and by design can work word-by-word incrementally. Hence, it can be used in highly-responsive interactive and situated settings. Using a corpus of descriptions from game-play between human subjects (who found this to be a challenging task), we show that reconstruction of description structure in our system contributes to task success and supports the performance of the word-based model of grounded semantics that we use.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{konovalov_collecting_2016,

title = {Collecting Better Training Data using Biased Agent Policies in Negotiation Dialogues},

author = {Vasily Konovalov and Oren Melamud and Ron Artstein and Ido Dagan},

url = {http://workshop.colips.org/wochat/documents/RP-270.pdf},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of WOCHAT, the Second Workshop on Chatbots and Conversational Agent Technologies},

publisher = {Zerotype},

address = {Los Angeles},

abstract = {When naturally occurring data is characterized by a highly skewed class distribution, supervised learning often benefits from reducing this skew. Human-agent dialogue data is commonly highly skewed when using standard agent policies. Hence, we suggest that agent policies need to be reconsidered in the context of training data collection. Specifically, in this work we implemented biased agent policies that are optimized for data collection in the negotiation domain. Empirical evaluations show that our method is successful in collecting a reasonably balanced corpus in the highly skewed Job-Candidate domain. Furthermore, using this balanced corpus to train a negotiation intent classifier yields notable performance improvements relative to naturally distributed data.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gratch_benefits_2016,

title = {The Benefits of Virtual Humans for Teaching Negotiation},

author = {Jonathan Gratch and David DeVault and Gale Lucas},

url = {http://iva2016.ict.usc.edu/wp-content/uploads/Papers/100110276.pdf},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of the 16th International Conference on Intelligent Virtual Agents (IVA), 2016},

publisher = {Springer},

address = {Los Angeles, CA},

abstract = {This article examines the potential for teaching negotiation with virtual humans. Many people find negotiations to be aversive. We conjecture that stu-dents may be more comfortable practicing negotiation skills with an agent than with another person. We test this using the Conflict Resolution Agent, a semi-automated virtual human that negotiates with people via natural language. In a between-participants design, we independently manipulated two pedagogically-relevant factors while participants engaged in repeated negotiations with the agent: perceived agency (participants either believed they were negotiating with a computer program or another person) and pedagogical feedback (participants received instructional advice or no advice between negotiations). Findings indi-cate that novice negotiators were more comfortable negotiating with a computer program (they self-reported more comfort and punished their opponent less of-ten) and expended more effort on the exercise following instructional feedback (both in time spent and in self-reported effort). These findings lend support to the notion of using virtual humans to teach interpersonal skills.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marge_assessing_2016,

title = {Assessing Agreement in Human-Robot Dialogue Strategies: A Tale of TwoWizards},

author = {Matthew Marge and Claire Bonial and Kimberly A. Pollard and Ron Artstein and Brendan Byrne and Susan G. Hill and Clare Voss and David Traum},

url = {http://iva2016.ict.usc.edu/wp-content/uploads/Papers/100110460.pdf},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of The Sixteenth International Conference on Intelligent Virtual Agents (IVA 2016),},

publisher = {Springer},

address = {Los Angeles, CA},

abstract = {The Wizard-of-Oz (WOz) method is a common experimental technique in virtual agent and human-robot dialogue research for eliciting natural communicative behavior from human partners when full autonomy is not yet possible. For the first phase of our research reported here, wizards play the role of dialogue manager, acting as a robot’s dialogue processing. We describe a novel step within WOz methodology that incorporates two wizards and control sessions: the wizards function much like corpus annotators, being asked to make independent judgments on how the robot should respond when receiving the same verbal commands in separate trials. We show that inter-wizard discussion after the control sessions and the resolution with a reconciled protocol for the follow-on pilot sessions successfully impacts wizard behaviors and significantly aligns their strategies. We conclude that, without control sessions, we would have been unlikely to achieve both the natural diversity of expression that comes with multiple wizards and a better protocol for modeling an automated system.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mizukami_analyzing_2016,

title = {Analyzing the Effect of Entrainment on Dialogue Acts},

author = {Masahiro Mizukami and Koichiro Yoshino and Graham Neubig and David Traum and Satoshi Nakamura},

url = {http://www.sigdial.org/workshops/conference17/proceedings/pdf/SIGDIAL40.pdf},

year  = {2016},

date = {2016-09-01},

booktitle = {Proceedings of the SIGDIAL 2016 Conference},

pages = {310–318},

publisher = {Association for Computational Linguistics},

address = {Los Angeles, CA},

abstract = {Entrainment is a factor in dialogue that affects not only human-human but also human-machine interaction. While entrainment on the lexical level is well documented, less is known about how entrainment affects dialogue on a more abstract, structural level. In this paper, we investigate the effect of entrainment on dialogue acts and on lexical choice given dialogue acts, as well as how entrainment changes during a dialogue. We also define a novel measure of entrainment to measure these various types of entrainment. These results may serve as guidelines for dialogue systems that would like to entrain with users in a similar manner.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_new_2016,

title = {New Dimensions in Testimony Demonstration},

author = {Ron Artstein and Alesia Gainer and Kallirroi Georgila and Anton Leuski and Ari Shapiro and David Traum},

url = {http://www.aclweb.org/anthology/N16-3007},

year  = {2016},

date = {2016-06-01},

booktitle = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations},

pages = {32–36},

publisher = {Association for Computational Linguistics},

address = {San Diego, California},

abstract = {New Dimensions in Testimony is a prototype dialogue system that allows users to conduct a conversation with a real person who is not available for conversation in real time. Users talk to a persistent representation of Holocaust survivor Pinchas Gutter on a screen, while a dialogue agent selects appropriate responses to user utterances from a set of pre-recorded video statements, simulating a live conversation. The technology is similar to existing conversational agents, but to our knowledge this is the first system to portray a real person. The demonstration will show the system on a range of screens (from mobile phones to large TVs), and allow users to have individual conversations with Mr. Gutter.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mizukami_word_2016,

title = {Word and Dialogue Act Entrainment Analysis based on User Profile},

author = {Masahiro Mizukami and David Traum and Koichiro Yoshino and Graham Neubig and Satoshi Nakamura},

url = {https://kaigi.org/jsai/webprogram/2016/pdf/356.pdf},

year  = {2016},

date = {2016-06-01},

booktitle = {Proceedings of The 30th Annual Conference of the Japanese Society for Artificial Intelligence},

address = {Kitakyushu, Japan},

abstract = {Patterns of dialogue act and word selection are observable in dialogue. Entrainment is the factor that might account for these patterns. We test the entrainment hypotheses using the switchboard corpus, comparing speech of different speakers from different parts of the dialogue, but also speech of the same speaker at different points. Our ⬚ndings replicate previous studies that dialogue participants converge toward each other in word choice, but we also investigate novel measures of entrainment of dialogue act selection, and word choice for speci⬚c dialogue acts. These studies inform a design for dialogue systems that would show human-like degrees of entrainment.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{uryupina_arrau_2016,

title = {ARRAU: Linguistically-Motivated Annotation of Anaphoric Descriptions},

author = {Olga Uryupina and Ron Artstein and Antonella Bristot and Federica Cavicchio and Kepa Rodriguez and Massimo Poesio},

url = {http://www.lrec-conf.org/proceedings/lrec2016/summaries/1121.html},

year  = {2016},

date = {2016-05-01},

booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},

pages = {2058–2062},

publisher = {European Language Resources Association (ELRA)},

address = {Portorož, Slovenia},

abstract = {This paper presents a second release of the ARRAU dataset: a multi-domain corpus with thorough linguistically motivated annotation of anaphora and related phenomena. Building upon the first release almost a decade ago, a considerable effort had been invested in improving the data both quantitatively and qualitatively. Thus, we have doubled the corpus size, expanded the selection of covered phenomena to include referentiality and genericity and designed and implemented a methodology for enforcing the consistency of the manual annotation. We believe that the new release of ARRAU provides a valuable material for ongoing research in complex cases of coreference as well as for a variety of related tasks. The corpus is publicly available through LDC.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@inproceedings{manuvinakurike_reducing_2015,

title = {Reducing the Cost of Dialogue System Training and Evaluation with Online, Crowd-Sourced Dialogue Data Collection},

author = {Ramesh Manuvinakurike and Maike Paetzel and David DeVault},

url = {http://ict.usc.edu/pubs/Reducing%20the%20Cost%20of%20Dialogue%20System%20Training%20and%20Evaluation%20with%20Online,%20Crowd-Sourced%20Dialogue%20Data%20Collection.pdf},

year  = {2015},

date = {2015-08-01},

booktitle = {Proceedings of SEMDIAL 2015 goDIAL},

pages = {113 – 121},

address = {Gothenburg, Sweden},

abstract = {This paper presents and analyzes an approach to crowd-sourced spoken dialogue data collection. Our approach enables low cost collection of browser-based spoken dialogue interactions between two remote human participants (human-human condition) as well as one remote human participant and an automated dialogue system (human-agent condition). We present a case study in which 200 remote participants were recruited to participate in a fast-paced image matching game, and which included both human-human and human-agent conditions. We discuss several technical challenges encountered in achieving this crowd-sourced data collection, and analyze the costs in time and money of carrying out the study. Our results suggest the potential of crowdsourced spoken dialogue data to lower costs and facilitate a range of research in dialogue modeling, dialogue system design, and system evaluation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gratch_exploring_2015,

title = {Exploring the Implications of Virtual Human Research for Human-Robot Teams},

author = {Jonathan Gratch and Susan Hill and Louis-Philippe Morency and David Pynadath and David Traum},

url = {http://ict.usc.edu/pubs/Exploring%20the%20Implications%20of%20Virtual%20Human%20Research%20for%20Human-Robot%20Teams.pdf},

doi = {10.1007/978-3-319-21067-4_20},

isbn = {978-3-319-21066-7 978-3-319-21067-4},

year  = {2015},

date = {2015-08-01},

booktitle = {Virtual, Augmented and Mixed Reality},

volume = {9179},

pages = {186–196},

publisher = {Springer International Publishing},

address = {Los Angeles, CA},

abstract = {This article briefly explores potential synergies between the fields of virtual human and human-robot interaction research. We consider challenges in advancing the effectiveness of human-robot teams makes recommendations for enhancing this by facilitating synergies between robotics and virtual human research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gratch_negotiation_2015,

title = {Negotiation as a Challenge Problem for Virtual Humans},

author = {Jonathan Gratch and David DeVault and Gale M. Lucas and Stacy Marsella},

editor = {Willem-Paul Brinkman and Joost Broekens and Dirk Heylen},

url = {http://ict.usc.edu/pubs/Negotiation%20as%20a%20Challenge%20Problem%20for%20Virtual%20Humans.pdf},

doi = {10.1007/978-3-319-21996-7_21},

isbn = {978-3-319-21995-0 978-3-319-21996-7},

year  = {2015},

date = {2015-08-01},

booktitle = {Intelligent Virtual Agents},

volume = {9238},

pages = {201–215},

publisher = {Springer International Publishing},

address = {Delft, Netherlands},

abstract = {We argue for the importance of negotiation as a challenge problem for virtual human research, and introduce a virtual conversational agent that allows people to practice a wide range of negotiation skills. We describe the multi-issue bargaining task, which has become a de facto standard for teaching and research on negotiation in both the social and computer sciences. This task is popular as it allows scientists or instructors to create a variety of distinct situations that arise in real-life negotiations, simply by manipulating a small number of mathematical parameters. We describe the development of a virtual human that will allow students to practice the interpersonal skills they need to recognize and navigate these situations. An evaluation of an early wizard-controlled version of the system demonstrates the promise of this technology for teaching negotiation and supporting scientific research on social intelligence.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nouri_cross_2015,

title = {Cross cultural report of values and decisions in the multi round ultimatum game and the centipede game},

author = {Elnaz Nouri and David Traum},

url = {http://ict.usc.edu/pubs/Cross%20cultural%20report%20of%20values%20and%20decisions%20in%20the%20multi%20round%20ultimatum%20game%20and%20the%20centipede%20game.pdf},

year  = {2015},

date = {2015-07-01},

booktitle = {Proceeding of AHFE 2015},

address = {Las Vegas, NV},

abstract = {This paper investigates the cultural differences in decision making behavior of people from the US and India. We study players from these cultures playing the Multi Round Ultimatum Game and the Centipede Game online. In order to study how people from different cultures evaluate decisions we use criteria from the Multi Attribute Relational Values (MARV) survey. Our results confirm the existence of cultural differences in how people from US and India make decisions in the Ultimatum and Centipede games. We also observe differences in responses to survey questions implying differences in the amount of importance that the two cultures assign to the MARV decision making criteria.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chatterjee_crmactive_2015,

title = {CRMActive: An Active Learning Based Approach for Effective Video Annotation and Retrieval},

author = {Moitreya Chatterjee and Anton Leuski},

url = {http://ict.usc.edu/pubs/CRMActive%20-%20An%20Active%20Learning%20Based%20Approach%20for%20Effective%20Video%20Annotation%20and%20Retrieval.pdf},

doi = {10.1145/2671188.2749342},

year  = {2015},

date = {2015-06-01},

booktitle = {Proceedings of ACM International Conference on Multimedia Retrieval (ICMR)},

pages = {535–538},

publisher = {ACM},

address = {Shanghai, China},

abstract = {Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [7]require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the training data, allows for a good performance even before the training data is fully annotated. In this work we propose an active learning algorithm, which combines a novel measure of sample uncertainty with a novel clustering-based approach for determining sample density and diversity and integrate it with NormCRM. The clusters are also iteratively re⬚ned to ensure both feature and label-level agreement among samples. We show that our approach outperforms multiple baselines both on a new, open dataset and on the popular TRECVID corpus at both the tasks of annotation and text-based retrieval of videos.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{garten_combining_2015,

title = {Combining Distributed Vector Representations for Words},

author = {Justin Garten and Kenji Sagae and Volkan Ustun and Morteza Dehghani},

url = {http://ict.usc.edu/pubs/Combining%20Distributed%20Vector%20Representations%20for%20Words.pdf},

year  = {2015},

date = {2015-06-01},

booktitle = {Proceedings of NAACL-HLT 2015},

pages = {95–101},

publisher = {Association for Computational Linguistics},

address = {Denver, Colorado},

abstract = {Recent interest in distributed vector representations for words has resulted in an increased diversity of approaches, each with strengths and weaknesses. We demonstrate how diverse vector representations may be inexpensively composed into hybrid representations, effectively leveraging strengths of individual components, as evidenced by substantial improvements on a standard word analogy task. We further compare these results over different sizes of training sets and find these advantages are more pronounced when training data is limited. Finally, we explore the relative impacts of the differences in the learning methods themselves and the size of the contexts they access.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_how_2015,

title = {How Many Utterances Are Needed to Support Time-Offset Interaction?},

author = {Ron Artstein and Anton Leuski and Heather Maio and Tomer Mor-Barak and Carla Gordon and David Traum},

url = {http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS15/paper/view/10442},

isbn = {978-1-57735-730-8},

year  = {2015},

date = {2015-05-01},

booktitle = {Proceedings of FLAIRS 28},

pages = {144–149},

publisher = {AAAI Press},

address = {Hollywood, FL},

abstract = {A set of several hundred recorded statements by a single speaker is sufficient to address unrestricted questions and sustain short conversations on a circumscribed topic. Statements were recorded by Pinchas Gutter, a Holocaust survivor, talking about his personal experiences before, during and after the Holocaust. These statements were delivered to participants in conversation, using a “Wizard of Oz” system, where live operators select an appropriate reaction to each user utterance in real time. Even though participants were completely unconstrained in the questions they could ask, the recorded statements were able to directly address at least 58% of user questions. The unanswered questions were then analyzed to identify gaps, and additional statements were recorded to fill the gaps. The statements will be put in an automated system using existing language understanding technology, to create the first full working system of time-offset interaction, allowing a live conversation with a real human who is not present for the conversation in real time.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shim_acoustic_2015,

title = {ACOUSTIC AND PARA-VERBAL INDICATORS OF PERSUASIVENESS IN SOCIAL MULTIMEDIA},

author = {Han Suk Shim and Sunghyun Park and Moitreya Chatterjee and Stefan Scherer and Kenji Sagae and Louis-Philippe Morency},

url = {http://ict.usc.edu/pubs/ACOUSTIC%20AND%20PARA-VERBAL%20INDICATORS%20OF%20PERSUASIVENESS%20IN%20SOCIAL%20MULTIMEDIA.pdf},

year  = {2015},

date = {2015-04-01},

booktitle = {Proceeding of ICASSP 2015},

pages = {2239 – 2243},

publisher = {IEEE},

address = {Brisbane, Australia},

abstract = {Persuasive communication and interaction play an important and pervasive role in many aspects of our lives. With the rapid growth of social multimedia websites such as YouTube, it has become more important and useful to understand persuasiveness in the context of online social multimedia content. In this paper, we present our resultsof conducting various analyses of persuasiveness in speech with our multimedia corpus of 1,000 movie review videos obtained from ExpoTV.com, a popular social multimedia website. Our experiments firstly show that a speaker’s level of persuasiveness can be predicted from acoustic characteristics and para-verbal cues related to speech fluency. Secondly, we show that taking acoustic cues in different time periods of a movie review can improve the performance of predicting a speaker’s level of persuasiveness. Lastly, we show that a speaker’s positive or negative attitude toward a topic influences the prediction performance as well.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{devault_toward_2015,

title = {Toward Natural Turn-Taking in a Virtual Human Negotiation Agent},

author = {David DeVault and Jonathan Mell and Jonathan Gratch},

url = {http://ict.usc.edu/pubs/Toward%20Natural%20Turn-Taking%20in%20a%20Virtual%20Human%20Negotiation%20Agent.pdf},

year  = {2015},

date = {2015-03-01},

booktitle = {AAAI Spring Symposium on Turn-taking and Coordination in Human-Machine Interaction},

pages = {2–9},

publisher = {AAAI Press},

address = {Palo Alto, California},

abstract = {In this paper we assess our progress toward creating a virtual human negotiation agent with fluid turn-taking skills. To facilitate the design of this agent, we have collected a corpus of human-human negotiation roleplays as well as a corpus of Wizard-controlled human-agent negotiations in the same roleplay scenario.We compare the natural turn-taking behavior in our human-human corpus with that achieved in our Wizard-of-Oz corpus, and quantify our virtual human’s turn-taking skills using a combination of subjective and objective metrics. We also discuss our design for a Wizard user interface to support real-time control of the virtual human’s turntaking and dialogue behavior, and analyze our wizard’s usage of this interface.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ward_ten_2015,

title = {Ten Challenges in Highly-Interactive Dialog Systems},

author = {Nigel G. Ward and David DeVault},

url = {http://ict.usc.edu/pubs/Ten%20Challenges%20in%20Highly-Interactive%20Dialog%20Systems.pdf},

year  = {2015},

date = {2015-03-01},

booktitle = {Proceedings of AAAI 2015 Spring Symposium},

address = {Palo Alto, CA},

abstract = {Systems capable of highly-interactive dialog have recently been developed in several domains. This paper considers how to build on these successes to make systems more robust, easier to develop, more adaptable, and more scientifically significant.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}