Publications

@inproceedings{rosenbloom_symmetry_2019,

title = {(A)symmetry × (Non)monotonicity: Towards a Deeper Understanding of Key Cognitive Di/Trichotomies and the Common Model of Cognition},

author = {Paul S Rosenbloom},

url = {https://iccm-conference.neocities.org/2019/proceedings/papers/ICCM2019_paper_6.pdf},

year  = {2019},

date = {2019-07-01},

booktitle = {In Proceedings of the 17th Annual Meeting of the International Conference on Cognitive Modeling},

pages = {6},

address = {Montreal, Canada},

abstract = {A range of dichotomies from across the cognitive sciences are reduced to either (a)symmetry or (non)monotonicity. Taking the cross-product of these two elemental dichotomies then yields a deeper understanding of both two key trichotomies –based on control and content hierarchies – and the Common Model of Cognition, with results that bear on the structure of integrative cognitive architectures, models and systems, and on their commonalities, differences and gaps.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{johnson_assessing_2019,

title = {Assessing Common Errors Students Make When Negotiating},

author = {Emmanuel Johnson and Sarah Roediger and Gale Lucas and Jonathan Gratch},

url = {http://dl.acm.org/citation.cfm?doid=3308532.3329470},

doi = {10.1145/3308532.3329470},

isbn = {978-1-4503-6672-4},

year  = {2019},

date = {2019-07-01},

booktitle = {Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents - IVA '19},

pages = {30–37},

publisher = {ACM Press},

address = {Paris, France},

abstract = {Research has shown that virtual agents can be effective tools for teaching negotiation. Virtual agents provide an opportunity for students to practice their negotiation skills which leads to better outcomes. However, these negotiation training agents often lack the ability to understand the errors students make when negotiating, thus limiting their effectiveness as training tools. In this article, we argue that automated opponent-modeling techniques serve as effective methods for diagnosing important negotiation mistakes. To demonstrate this, we analyze a large number of participant traces generated while negotiating with a set of automated opponents. We show that negotiators’ performance is closely tied to their understanding of an opponent’s preferences. We further show that opponent modeling techniques can diagnose specific errors including: failure to elicit diagnostic information from an opponent, failure to utilize the information that was elicited, and failure to understand the transparency of an opponent. These results show that opponent modeling techniques can be effective methods for diagnosing and potentially correcting crucial negotiation errors.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lucas_effectiveness_2019,

title = {The Effectiveness of Social Influence Tactics when Used by a Virtual Agent},

author = {Gale M. Lucas and Janina Lehr and Nicole Krämer and Jonathan Gratch},

url = {http://dl.acm.org/citation.cfm?doid=3308532.3329464},

doi = {10.1145/3308532.3329464},

isbn = {978-1-4503-6672-4},

year  = {2019},

date = {2019-07-01},

booktitle = {Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents - IVA '19},

pages = {22–29},

publisher = {ACM Press},

address = {Paris, France},

abstract = {Research in social science distinguishes between two types of social influence: informational and normative. Informational social influence is driven by the desire to evaluate ambiguous situations correctly, whereas normative social influence is driven by the desire to be liked and gain social acceptance from another person. Although we know from research that humans can effectively use either of these techniques to persuade other humans, scholars have yet to examine the relative effectiveness of informational versus normative social influence when used by virtual agents. We report a study in which users interact with a system that persuades them either using informational or normative social influence. Furthermore, to compare agents to human interlocutors, users are told that the system is either teleoperated by a human (avatar) or fully-automated (agent). Using this design, we are able to compare the effectiveness of virtual agents (vs humans) in employing informational versus normative social influence. Participants interacted with the system, which employed a Wizard-of-Oz operated virtual agent that tried to persuade the user to agree with its rankings on a “survival task.” Controlling for initial divergence in rankings between user and the agent, there was a significant main effect such that informational social influence resulted in greater influence than normative influence. However, this was qualified by an interaction that approached significance; users were, if anything, more persuaded by informational influence when they believe the agent was AI (compared to a human), whereas there was no difference between the agent and avatar in the normative influence condition.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sohail_blissymbolics_2019,

title = {A Blissymbolics Translation System},

author = {Usman Sohail and David Traum},

url = {http://aclweb.org/anthology/W19-1705},

doi = {10.18653/v1/W19-1705},

year  = {2019},

date = {2019-06-01},

booktitle = {Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies},

pages = {32–36},

publisher = {Association for Computational Linguistics},

address = {Minneapolis, Minnesota},

abstract = {Blissymbolics (Bliss) is a pictographic writing system that is used by people with communication disorders. Bliss attempts to create a writing system that makes words easier to distinguish by using pictographic symbols that encapsulate meaning rather than sound, as the English alphabet does for example. Users of Bliss rely on human interpreters to use Bliss. We created a translation system from Bliss to natural English with the hopes of decreasing the reliance on human interpreters by the Bliss community. We first discuss the basic rules of Blissymbolics. Then we point out some of the challenges associated with developing computer assisted tools for Blissymbolics. Next we talk about our ongoing work in developing a translation system, including current limitations, and future work. We conclude with a set of examples showing the current capabilities of our translation system.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{song_polysemous_2019,

title = {Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval},

author = {Yale Song and Mohammad Soleymani},

url = {https://arxiv.org/abs/1906.04402},

year  = {2019},

date = {2019-06-01},

booktitle = {Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

pages = {10},

publisher = {IEEE},

address = {Long Beach, CA},

abstract = {Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively handle polysemous instances with multiple possible meanings; at best, it would find an average representation of different meanings. This hinders its use in real-world scenarios where individual instances and their cross-modal associations are often ambiguous. In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning. To learn visual-semantic embedding, we tie-up two PIE-Nets and optimize them jointly in the multiple instance learning framework. Most existing work on cross-modal retrieval focus on image-text pairs of data. Here, we also tackle a more challenging case of video-text retrieval. To facilitate further research in video-text retrieval, we release a new dataset of 50K video-sentence pairs collected from social media, dubbed MRW (my reaction when). We demonstrate our approach on both image-text and video-text retrieval scenarios using MS-COCO, TGIF, and our new MRW dataset.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gilani_can_2019,

title = {Can a Virtual Human Facilitate Language Learning in a Young Baby?},

author = {Setareh Nasihati Gilani and David Traum and Rachel Sortino and Grady Gallagher and Kailyn Aaron-lozano and Cryss Padilla and Ari Shapiro and Jason Lamberton and Laura-ann Petitto},

url = {https://dl.acm.org/citation.cfm?id=3332035},

isbn = {978-1-4503-6309-9},

year  = {2019},

date = {2019-05-01},

booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},

publisher = {ACM},

address = {Montreal, Canada},

abstract = {There is a significant paucity of work on language learning systems for young infants [2, 5, 19] despite the widely understood critical importance that this developmental period has for healthy language and cognitive growth, and related reading and academic success [6, 14]. Deaf babies constitute one vulnerable population as they can experience dramatically reduced or no access to usable linguistic input during this period [18]. This causes potentially devastating impact on children's linguistic, cognitive, and social skills [9, 10, 15, 16, 20]. We introduced an AI system, called RAVE (Robot, AVatar, thermal Enhanced language learning tool), designed specifically for babies within the age range of 6-12 months [8, 17]. RAVE consists of two agents: a virtual human (provides language and socially contingent interactions) and an embodied robot (provides socially engaging physical cues to babies and directs babies' attention to the virtual human). Detailed description of the system's constituent components and dialogue algorithms are presented in [17] and [8].},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{koeman_recognising_2019,

title = {Recognising and Explaining Bidding Strategies in Negotiation Support Systems},

author = {Vincent J Koeman and Koen V Hindriks and Jonathan Gratch and Catholijn M Jonker},

url = {https://dl.acm.org/citation.cfm?id=3332011},

isbn = {978-1-4503-6309-9},

year  = {2019},

date = {2019-05-01},

booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},

pages = {3},

publisher = {ACM},

address = {Montreal, Canada},

abstract = {To improve a negotiator's ability to recognise bidding strategies, we pro-actively provide explanations that are based on the opponent's bids and the negotiator's guesses about the opponent's strategy. We introduce an aberration detection mechanism for recognising strategies and the notion of an explanation matrix. The aberration detection mechanism identifies when a bid falls outside the range of expected behaviour for a specific strategy. The explanation matrix is used to decide when to provide what explanations. We evaluated our work experimentally in a task in which participants are asked to identify their opponent's strategy in the environment of a negotiation support system, namely the Pocket Negotiator (PN). We implemented our explanation mechanism in the PN and experimented with different explanation matrices. As the number of correct guesses increases with explanations, indirectly, these experiments show the effectiveness of our aberration detection mechanism. Our experiments with over 100 participants show that suggesting consistent strategies is more effective than explaining why observed behaviour is inconsistent.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_using_2019,

title = {Using Reinforcement Learning to Optimize the Policies of an Intelligent Tutoring System for Interpersonal Skills Training},

author = {Kallirroi Georgila and Mark G Core and Benjamin D Nye and Shamya Karumbaiah and Daniel Auerbach and Maya Ram},

url = {http://www.ifaamas.org/Proceedings/aamas2019/pdfs/p737.pdf},

year  = {2019},

date = {2019-05-01},

booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},

pages = {9},

publisher = {IFAAMAS},

address = {Montreal, Canada},

abstract = {Reinforcement Learning (RL) has been applied successfully to Intelligent Tutoring Systems (ITSs) in a limited set of well-defined domains such as mathematics and physics. This work is unique in using a large state space and for applying RL to tutoring interpersonal skills. Interpersonal skills are increasingly recognized as critical to both social and economic development. In particular, this work enhances an ITS designed to teach basic counseling skills that can be applied to challenging issues such as sexual harassment and workplace conflict. An initial data collection was used to train RL policies for the ITS, and an evaluation with human participants compared a hand-crafted ITS which had been used for years with students (control) versus the new ITS guided by RL policies. The RL condition differed from the control condition most notably in the strikingly large quantity of guidance it provided to learners. Both systems were effective and there was an overall significant increase from pre- to post-test scores. Although learning gains did not differ significantly between conditions, learners had a significantly higher self-rating of confidence in the RL condition. Confidence and learning gains were both part of the reward function used to train the RL policies, and it could be the case that there was the most room for improvement in confidence, an important learner emotion. Thus, RL was successful in improving an ITS for teaching interpersonal skills without the need to prune the state space (as previously done).},

keywords = {Learning Sciences, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chaffey_developing_2019,

title = {Developing a Virtual Reality Wildfire Simulation to Analyze Human Communication and Interaction with a Robotic Swarm During Emergencies},

author = {Patricia Chaffey and Ron Artstein and Kallirroi Georgila and Kimberly A. Pollard and Setareh Nasihati Gilani and David M. Krum and David Nelson and Kevin Huynh and Alesia Gainer and Seyed Hossein Alavi and Rhys Yahata and David Traum},

url = {http://www-scf.usc.edu/ nasihati/publications/HLTCEM_2019.pdf},

year  = {2019},

date = {2019-05-01},

booktitle = {Proceedings of the 9th Language and Technology Conference},

publisher = {LTC},

address = {Poznań, Poland},

abstract = {Search and rescue missions involving robots face multiple challenges. The ratio of operators to robots is frequently one to one or higher, operators tasked with robots must contend with cognitive overload for long periods, and the robots themselves may be discomfiting to located survivors. To improve on the current state, we propose a swarm of robots equipped with natural language abilities and guided by a central virtual “spokesperson” able to access “plays”. The spokesperson may assist the operator with tasking the robots in their exploration of a zone, which allows the operator to maintain a safe distance. The use of multiple robots enables rescue personnel to cover a larger swath of ground, and the natural language component allows the robots to communicate with survivors located on site. This capability frees the operator to handle situations requiring personal attention, and overall can accelerate the location and assistance of survivors. In order to develop this system, we are creating a virtual reality simulation, in order to conduct a study and analysis of how humans communicate with these swarms of robots. The data collected from this experiment will inform how to best design emergency response swarm robots that are effectively able to communicate with the humans around them.},

keywords = {ARL, DoD, MxR, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gervits_classication-based_2019,

title = {A Classification-Based Approach to Automating Human-Robot Dialogue},

author = {Felix Gervits and Anton Leuski and Claire Bonial and Carla Gordon and David Traum},

url = {https://www.semanticscholar.org/paper/A-Classification-Based-Approach-to-Automating-Gervits-Leuski/262cf9e3a14e370d46a5e65f7872b32482d9ea69?tab=abstract&citingPapersSort=is-influential&citingPapersLimit=10&citingPapersOffset=0&year%5B0%5D=&year%5B1%5D=&citedPapersSort=is-influential&citedPapersLimit=10&citedPapersOffset=10},

year  = {2019},

date = {2019-04-01},

booktitle = {Proceedings of IWSDS 2019},

pages = {12},

address = {Siracusa, Italy},

abstract = {We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue including two wizards: one standing in for dialogue capabilities and another for navigation. Below, we describe the implementation details of the classifier and show how it was used to automate the dialogue wizard. We evaluate our system on several sets of source data from the corpus and find that response accuracy is generally high, even with very limited training data. Another contribution of this work is the novel demonstration of a dialogue manager that uses the classifier to engage in multi-floor dialogue with two different human roles. Overall, this approach is useful for enabling spoken dialogue systems to produce robust and accurate responses to natural language input, and for robots that need to interact with humans in a team setting.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bernardet_speech_2019,

title = {Speech Breathing in Virtual Humans: An Interactive Model and Empirical Study},

author = {Ulysses Bernardet and Sin-Hwa Kanq and Andrew Feng and Steve DiPaola and Ari Shapiro},

url = {https://ieeexplore.ieee.org/document/8714737/},

doi = {10.1109/VHCIE.2019.8714737},

isbn = {978-1-72813-219-8},

year  = {2019},

date = {2019-03-01},

booktitle = {2019 IEEE Virtual Humans and Crowds for Immersive Environments (VHCIE)},

pages = {1–9},

publisher = {IEEE},

address = {Osaka, Japan},

abstract = {Human speech production requires the dynamic regulation of air through the vocal system. While virtual character systems commonly are capable of speech output, they rarely take breathing during speaking – speech breathing – into account. We believe that integrating dynamic speech breathing systems in virtual characters can significantly contribute to augmenting their realism. Here, we present a novel control architecture aimed at generating speech breathing in virtual characters. This architecture is informed by behavioral, linguistic and anatomical knowledge of human speech breathing. Based on textual input and controlled by a set of lowand high-level parameters, the system produces dynamic signals in real-time that control the virtual character’s anatomy (thorax, abdomen, head, nostrils, and mouth) and sound production (speech and breathing).},

keywords = {MxR, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gordon_primer_2019,

title = {PRIMER: An Emotionally Aware Virtual Agent},

author = {Carla Gordon and Anton Leuski and Grace Benn and Eric Klassen and Edward Fast and Matt Liewer and Arno Hartholt and David Traum},

url = {https://www.research.ibm.com/haifa/Workshops/user2agent2019/},

year  = {2019},

date = {2019-03-01},

booktitle = {Proceedings of the 24th International Conference on Intelligent User Interfaces},

pages = {10},

publisher = {ACM},

address = {Los Angeles, CA},

abstract = {PRIMER is a proof-of-concept system designed to show the potential of immersive dialogue agents and virtual environments that adapt and respond to both direct verbal input and indirect emotional input. The system has two novel interfaces: (1) for the user, an immersive VR environment and an animated virtual agent both of which adapt and react to the user’s direct input as well as the user’s perceived emotional state, and (2) for an observer, an interface that helps track the perceived emotional state of the user, with visualizations to provide insight into the system’s decision making process. While the basic system architecture can be adapted for many potential real world applications, the initial version of this system was designed to assist clinical social workers in helping children cope with bullying. The virtual agent produces verbal and non-verbal behaviors guided by a plan for the counseling session, based on in-depth discussions with experienced counselors, but is also reactive to both initiatives that the user takes, e.g. asking their own questions, and the user’s perceived emotional state.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_digital_2019,

title = {Digital Survivor of Sexual Assault},

author = {Ron Artstein and Carla Gordon and Usman Sohail and Chirag Merchant and Andrew Jones and Julia Campbell and Matthew Trimmer and Jeffrey Bevington and COL Christopher Engen and David Traum},

url = {https://doi.org/10.1145/3301275.3302303},

doi = {10.1145/3301275.3302303},

isbn = {978-1-4503-6272-6},

year  = {2019},

date = {2019-03-01},

booktitle = {Proceedings of the 24th International Conference on Intelligent User Interfaces},

pages = {417–425},

publisher = {ACM},

address = {Marina del Rey, California},

abstract = {The Digital Survivor of Sexual Assault (DS2A) is an interface that allows a user to have a conversational experience with a survivor of sexual assault, using Artificial Intelligence technology and recorded videos. The application uses a statistical classifier to retrieve contextually appropriate pre-recorded video utterances by the survivor, together with dialogue management policies which enable users to conduct simulated conversations with the survivor about the sexual assault, its aftermath, and other pertinent topics. The content in the application has been specifically elicited to support the needs for the training of U.S. Army professionals in the Sexual Harassment/Assault Response and Prevention (SHARP) Program, and the application comes with an instructional support package. The system has been tested with approximately 200 users, and is presently being used in the SHARP Academy's capstone course.},

keywords = {DoD, Graphics, MedVR, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bonsch_volumetric_2019,

title = {Volumetric Video Capture using Unsynchronized, Low-cost Cameras:},

author = {Andrea Bönsch and Andrew Feng and Parth Patel and Ari Shapiro},

url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0007373202550261},

doi = {10.5220/0007373202550261},

isbn = {978-989-758-354-4},

year  = {2019},

date = {2019-02-01},

booktitle = {Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications},

pages = {255–261},

publisher = {SCITEPRESS - Science and Technology Publications},

address = {Prague, Czech Republic},

abstract = {Volumetric video can be used in virtual and augmented reality applications to show detailed animated performances by human actors. In this paper, we describe a volumetric capture system based on a photogrammetry cage with unsynchronized, low-cost cameras which is able to generate high-quality geometric data for animated avatars. This approach requires, inter alia, a subsequent synchronization of the captured videos.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang_addressing_2018,

title = {Addressing Sexist Attitudes on a College Campus through Virtual Role-Play with Digital Doppelgangers},

author = {Ning Wang and David Schwartz and Gabrielle Lewine and Ari Shapiro and Andrew Feng and Cindy Zhuang},

url = {http://dl.acm.org/citation.cfm?doid=3267851.3267913},

doi = {10.1145/3267851.3267913},

isbn = {978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents - IVA '18},

pages = {219–226},

publisher = {ACM Press},

address = {Sydney, NSW, Australia},

abstract = {Digital doppelgangers are virtual humans that highly resemble the real self but behave independently. Digital doppelgangers possess great potential to serve as powerful models for behavioral change. An emerging technology, the Rapid Avatar Capture and Simulation (RACAS) system, enables low-cost and high-speed scanning of a human user and creation of a digital doppelganger that is a fully animatable virtual 3D model of the user. We designed a virtual role-playing game, DELTA, that implements a powerful cognitive dissonance-based paradigm for attitudinal and behavioral change, and integrated it with digital doppelgangers to influence a human user’s attitude towards sexism on college campuses. In this paper, we discuss the design and evaluation the RACAS system and the DELTA game-based environment. Results indicate the potential impact of the DELTA game-based environment in creating an immersive virtual experience for attitudinal change.},

keywords = {Social Simulation, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mell_towards_2018,

title = {Towards a Repeated Negotiating Agent that Treats People Individually: Cooperation, Social Value Orientation, & Machiavellianism},

author = {Johnathan Mell and Gale Lucas and Sharon Mozgai and Jill Boberg and Ron Artstein and Jonathan Gratch},

url = {https://dl.acm.org/citation.cfm?id=3267910},

doi = {10.1145/3267851.3267910},

isbn = {ISBN: 978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},

pages = {125–132},

publisher = {ACM},

address = {Sydney, Australia},

abstract = {We present the results of a study in which humans negotiate with computerized agents employing varied tactics over a repeated number of economic ultimatum games. We report that certain agents are highly effective against particular classes of humans: several individual difference measures for the human participant are shown to be critical in determining which agents will be successful. Asking for favors works when playing with pro-social people but backfires with more selfish individuals. Further, making poor offers invites punishment from Machiavellian individuals. These factors may be learned once and applied over repeated negotiations, which means user modeling techniques that can detect these differences accurately will be more successful than those that don’t. Our work additionally shows that a significant benefit of cooperation is also present in repeated games—after sufficient interaction. These results have deep significance to agent designers who wish to design agents that are effective in negotiating with a broad swath of real human opponents. Furthermore, it demonstrates the effectiveness of techniques which can reason about negotiation over time.},

keywords = {VHTL, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gordon_evaluating_2018,

title = {Evaluating Subjective Feedback for Internet of Things Dialogues},

author = {Carla Gordon and Kallirroi Georgila and Hyungtak Choi and Jill Boberg and David Traum},

url = {https://amubox.univ-amu.fr/s/6YcAg3TpLpfzGEn#pdfviewer},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue},

pages = {64–72},

address = {Aix-en-Provence, France},

abstract = {This paper discusses the process of determining which subjective features are seen as ideal in a dialogue system, and linking these features to objectively quantifiable behaviors. A corpus of simulated system-user dialogues in the Internet of Things domain was manually annotated with a set of system communicative and action responses, and crowd-sourced ratings and qualitative feedback of these dialogues were collected. This corpus of subjective feedback was analyzed, revealing that raters described top ranked dialogues as Intelligent, Natural, Pleasant, and as having Personality. Additionally, certain communicative and action responses were statistically more likely to be present in dialogues described as having these features. There was also found to be a lack of agreement among raters as to whether a direct communication style, or a conversational one was preferred, suggesting that future research and development should consider creating models for different communication styles.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ustun_controlling_2018,

title = {Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma},

author = {Volkan Ustun and Paul S Rosenbloom and Seyed Sajjadi and Jeremy Nuttall},

url = {http://bcf.usc.edu/ rosenblo/Pubs/Ustun_IITSEC2018_D.pdf},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of I/ITSEC 2018},

publisher = {National Training and Simulation Association},

address = {Orlando, FL},

abstract = {Simulations, along with other similar applications like virtual worlds and video games, require computational models of intelligence that generate realistic and credible behavior for the participating synthetic characters. Cognitive architectures, which are models of the fixed structure underlying intelligent behavior in both natural and artificial systems, provide a conceptually valid common basis, as evidenced by the current efforts towards a standard model of the mind, to generate human-like intelligent behavior for these synthetic characters. Developments in the field of artificial intelligence, mainly in probabilistic graphical models and neural networks, open up new opportunities for cognitive architectures to make the synthetic characters more autonomous and to enrich their behavior. Sigma (Σ) is a cognitive architecture and system that strives to combine what has been learned from four decades of independent work on symbolic cognitive architectures, probabilistic graphical models, and more recently neural models, under its graphical architecture hypothesis. Sigma leverages an extended form of factor graphs towards a uniform grand unification of not only traditional cognitive capabilities but also key non-cognitive aspects, creating unique opportunities for the construction of new kinds of cognitive models that possess a Theory-of-Mind and that are perceptual, autonomous, interactive, affective, and adaptive. In this paper, we will introduce Sigma along with its diverse capabilities and then use three distinct proof-of-concept Sigma models to highlight combinations of these capabilities: (1) Distributional reinforcement learning models in a simple OpenAI Gym problem; (2) A pair of adaptive and interactive agent models that demonstrate rule-based, probabilistic, and social reasoning in a physical security scenario instantiated within the SmartBody character animation platform; and (3) A knowledge-free exploration model in which an agent leverages only architectural appraisal variables, namely attention and curiosity, to locate an item while building up a map in a Unity environment.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoegen_impact_2018,

title = {The impact of agent facial mimicry on social behavior in a prisoner’s dilemma},

author = {Rens Hoegen and Job Van Der Schalk and Gale Lucas and Jonathan Gratch},

url = {https://dl.acm.org/citation.cfm?id=3267911},

doi = {10.1145/3267851.3267911},

isbn = {978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},

pages = {275–280},

publisher = {ACM},

address = {Sydney, Australia},

abstract = {A long tradition of research suggests a relationship between emotional mimicry and pro-social behavior, but the nature of this relationship is unclear. Does mimicry cause rapport and cooperation, or merely reflect it? Virtual humans can provide unique insights into these social processes by allowing unprecedented levels of experimental control. In a 2 x 2 factorial design, we examined the impact of facial mimicry and counter-mimicry in the iterated prisoner’s dilemma. Participants played with an agent that copied their smiles and frowns or one that showed the opposite pattern – i.e., that frowned when they smiled. As people tend to smile more than frown, we independently manipulated the contingency of expressions to ensure any effects are due to mimicry alone, and not the overall positivity/negativity of the agent: i.e., participants saw either a reflection of their own expressions or saw the expressions shown to a previous participant. Results show that participants smiled significantly more when playing an agent that mimicked them. Results also show a complex association between smiling, feelings of rapport, and cooperation. We discuss the implications of these findings on virtual human systems and theories of cooperation.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lucas_effects_2018,

title = {Effects of Perceived Agency and Message Tone in Responding to a Virtual Personal Trainer},

author = {Gale M Lucas and Nicole Kramer and Clara Peters and Lisa-Sophie Taesch and Johnathan Mell and Jonathan Gratch},

url = {https://dl.acm.org/citation.cfm?id=3267855},

doi = {10.1145/3267851.3267855},

isbn = {978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},

pages = {247–254},

publisher = {ACM},

address = {Sydney, Australia},

abstract = {Research has demonstrated promising benefits of applying virtual trainers to promote physical fitness. The current study investigated the value of virtual agents in the context of personal fitness, compared to trainers with greater levels of perceived agency (avatar or live human). We also explored the possibility that the effectiveness of the virtual trainer might depend on the affective tone it uses when trying to motivate users. Accordingly, participants received either positively or negatively valenced motivational messages from a virtual human they believed to be either an agent or an avatar, or they received the messages from a human instructor via skype. Both self-report and physiological data were collected. Like in-person coaches, the live human trainer who used negatively valenced messages were well-regarded; however, when the agent or avatar used negatively valenced messages, participants responded more poorly than when they used positively valenced ones. Perceived agency also affected rapport: compared to the agent, users felt more rapport with the live human trainer or the avatar. Regardless of trainer type, they also felt more rapport - and said they put in more effort - with trainers that used positively valenced messages than those that used negatively valenced ones. However, in reality, they put in more physical effort (as measured by heart rate) when trainers employed the more negatively valenced affective tone. We discuss implications for human–computer interaction.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mell_results_2018,

title = {Results of the First Annual Human-Agent League of the Automated Negotiating Agents Competition},

author = {Johnathan Mell and Jonathan Gratch and Tim Baarslag and Reyhan Aydogran and Catholijn M Jonker},

url = {https://dl.acm.org/citation.cfm?id=3267907},

doi = {10.1145/3267851.3267907},

isbn = {978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},

pages = {23–28},

publisher = {ACM},

address = {Sydney, Australia},

abstract = {We present the results of the first annual Human-Agent League of ANAC. By introducing a new human-agent negotiating platform to the research community at large, we facilitated new advancements in human-aware agents. This has succeeded in pushing the envelope in agent design, and creating a corpus of useful human-agent interaction data. Our results indicate a variety of agents were submitted, and that their varying strategies had distinct outcomes on many measures of the negotiation. These agents approach the problems endemic to human negotiation, including user modeling, bidding strategy, rapport techniques, and strategic bargaining. Some agents employed advanced tactics in information gathering or emotional displays and gained more points than their opponents, while others were considered more “likeable” by their partners.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lucas_culture_2018,

title = {Culture, Errors, and Rapport-building Dialogue in Social Agents},

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

url = {https://dl.acm.org/citation.cfm?id=3267887},

doi = {10.1145/3267851.3267887},

isbn = {978-1-4503-6013-5},

year  = {2018},

date = {2018-11-01},

booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},

pages = {51–58},

publisher = {ACM},

address = {Sydney, Australia},

abstract = {This work explores whether culture impacts the extent to which social dialogue can mitigate (or exacerbate) the loss of trust caused when agents make conversational errors. Our study uses an agent designed to persuade users to agree with its rankings on two tasks. Participants from the U.S. and Japan completed our study. We perform two manipulations: (1) The presence of conversational errors – the agent exhibited errors in the second task or not; (2) The presence of social dialogue – between the two tasks, users either engaged in a social dialogue with the agent or completed a control task. Replicating previous research, conversational errors reduce the agent’s influence. However, we found that culture matters: there was a marginally significant three-way interaction with culture, presence of social dialogue, and presence of errors. The pattern of results suggests that, for American participants, social dialogue backfired if it is followed by errors, presumably because it extends the period of good performance, creating a stronger contrast effect with the subsequent errors. However, for Japanese participants, social dialogue if anything mitigates the detrimental effect of errors; the negative effect of errors is only seen in the absence of a social dialogue. Agent design should therefore take the culture of the intended users into consideration when considering use of social dialogue to bolster agents against conversational errors.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marge_balancing_2018,

title = {Balancing Efficiency and Coverage in Human-Robot Dialogue Collection},

author = {Matthew Marge and Claire Bonial and Stephanie M. Lukin and Cory J. Hayes and Ashley Foots and Ron Artstein and Cassidy Henry and Kimberly A. Pollard and Carla Gordon and Felix Gervits and Anton Leuski and Susan G. Hill and Clare R. Voss and David Traum},

url = {https://arxiv.org/abs/1810.02017},

year  = {2018},

date = {2018-10-01},

booktitle = {Proceedings of the AAAI Fall Symposium on Interactive Learning in Artificial Intelligence for Human-Robot Interaction},

publisher = {arXiv},

address = {Arlington, Virginia},

abstract = {We describe a multi-phased Wizard-of-Oz approach to collecting human-robot dialogue in a collaborative search and navigation task. The data is being used to train an initial automated robot dialogue system to support collaborative exploration tasks. In the first phase, a wizard freely typed robot utterances to human participants. For the second phase, this data was used to design a GUI that includes buttons for the most common communications, and templates for communications with varying parameters. Comparison of the data gathered in these phases show that the GUI enabled a faster pace of dialogue while still maintaining high coverage of suitable responses, enabling more efficient targeted data collection, and improvements in natural language understanding using GUI-collected data. As a promising first step towardsinteractivelearning,thisworkshowsthatourapproach enables the collection of useful training data for navigationbased HRI tasks.},

keywords = {ARL, DoD, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nasihati_gilani_multimodal_2018,

title = {Multimodal Dialogue Management for Multiparty Interaction with Infants},

author = {Setareh Nasihati Gilani and David Traum and Arcangelo Merla and Eugenia Hee and Zoey Walker and Barbara Manini and Grady Gallagher and Laura-Ann Petitto},

url = {http://dl.acm.org/citation.cfm?doid=3242969.3243029},

doi = {10.1145/3242969.3243029},

isbn = {978-1-4503-5692-3},

year  = {2018},

date = {2018-10-01},

booktitle = {Proceedings of the 2018 on International Conference on Multimodal Interaction - ICMI '18},

pages = {5–13},

publisher = {ACM Press},

address = {Boulder, CO, USA},

abstract = {We present dialogue management routines for a system to engage in multiparty agent-infant interaction. The ultimate purpose of this research is to help infants learn a visual sign language by engaging them in naturalistic and socially contingent conversations during an early-life critical period for language development (ages 6 to 12 months) as initiated by an artificial agent. As a first step, we focus on creating and maintaining agent-infant engagement that elicits appropriate and socially contingent responses from the baby. Our system includes two agents, a physical robot and an animated virtual human. The system's multimodal perception includes an eye-tracker (measures attention) and a thermal infrared imaging camera (measures patterns of emotional arousal). A dialogue policy is presented that selects individual actions and planned multiparty sequences based on perceptual inputs about the baby's internal changing states of emotional engagement. The present version of the system was evaluated in interaction with 8 babies. All babies demonstrated spontaneous and sustained engagement with the agents for several minutes, with patterns of conversationally relevant and socially contingent behaviors. We further performed a detailed case-study analysis with annotation of all agent and baby behaviors. Results show that the baby's behaviors were generally relevant to agent conversations and contained direct evidence for socially contingent responses by the baby to specific linguistic samples produced by the avatar. This work demonstrates the potential for language learning from agents in very young babies and has especially broad implications regarding the use of artificial agents with babies who have minimal language exposure in early life.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{aljanaki_data-driven_2018,

title = {A data-driven approach to mid-level perceptual musical feature modeling},

author = {Anna Aljanaki and Mohammad Soleymani},

url = {https://arxiv.org/abs/1806.04903},

year  = {2018},

date = {2018-09-01},

booktitle = {Proceedings of the 19th International Society for Music Information Retrieval Conference},

publisher = {arXiv},

address = {Paris, France},

abstract = {Musical features and descriptors could be coarsely divided into three levels of complexity. The bottom level contains the basic building blocks of music, e.g., chords, beats and timbre. The middle level contains concepts that emerge from combining the basic blocks: tonal and rhythmic stability, harmonic and rhythmic complexity, etc. High-level descriptors (genre, mood, expressive style) are usually modeled using the lower level ones. The features belonging to the middle level can both improve automatic recognition of high-level descriptors, and provide new music retrieval possibilities. Mid-level features are subjective and usually lack clear definitions. However, they are very important for human perception of music, and on some of them people can reach high agreement, even though defining them and therefore, designing a hand-crafted feature extractor for them can be difficult. In this paper, we derive the mid-level descriptors from data. We collect and release a datasettextbackslashtextbackslashtextbackslashtextbackslashfootnotehttps://osf.io/5aupt/ of 5000 songs annotated by musicians with seven mid-level descriptors, namely, melodiousness, tonal and rhythmic stability, modality, rhythmic complexity, dissonance and articulation. We then compare several approaches to predicting these descriptors from spectrograms using deep-learning. We also demonstrate the usefulness of these mid-level features using music emotion recognition as an application.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rayatdoost_cross-corpus_2018,

title = {CROSS-CORPUS EEG-BASED EMOTION RECOGNITION},

author = {Soheil Rayatdoost and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/8517037/},

doi = {10.1109/MLSP.2018.8517037},

isbn = {978-1-5386-5477-4},

year  = {2018},

date = {2018-09-01},

booktitle = {2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)},

pages = {1–6},

publisher = {IEEE},

address = {Aalborg, Denmark},

abstract = {Lack of generalization is a common problem in automatic emotion recognition. The present study aims to explore the suitability of the existing EEG features for emotion recognition and investigate the performance of emotion recognition methods across different corpora. We introduce a novel dataset which includes spontaneous emotions and was analyzed in addition to the existing datasets for cross-corpus evaluation. We demonstrate that the performance of the existing methods significantly decreases when evaluated across different corpora. The best results are obtained by a convolutional neural network fed by spectral topography maps from different bands. We provide some evidence that stimuli-related sensory information is learned by machine learning models for emotion recognition using EEG signals.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manuvinakurike_dialedit_2018,

title = {DialEdit: Annotations for Spoken Conversational Image Editing},

author = {Ramesh Manuvinakurike and Jacqueline Brixey and Trung Bui and Walter Chang and Ron Artstein and Kallirroi Georgila},

url = {https://aclanthology.info/papers/W18-4701/w18-4701},

year  = {2018},

date = {2018-08-01},

booktitle = {Proceedings of the 14th Joint ACL - ISO Workshop on Interoperable Semantic Annotation},

publisher = {Association for Computational Linguistics},

address = {Santa Fe, New Mexico},

abstract = {We present a spoken dialogue corpus and annotation scheme for conversational image editing, where people edit an image interactively through spoken language instructions. Our corpus contains spoken conversations between two human participants: users requesting changes to images and experts performing these modifications in real time. Our annotation scheme consists of 26 dialogue act labels covering instructions, requests, and feedback, together with actions and entities for the content of the edit requests. The corpus supports research and development in areas such as incremental intent recognition, visual reference resolution, image-grounded dialogue modeling, dialogue state tracking, and user modeling.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mell_welcome_2018,

title = {Welcome to the Real World: How Agent Strategy Increases Human Willingness to Deceive},

author = {Johnathan Mell and Gale M. Lucas and Jonathan Gratch},

url = {https://dl.acm.org/citation.cfm?id=3237884},

year  = {2018},

date = {2018-07-01},

booktitle = {Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems},

pages = {1250–1257},

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

address = {Stockholm, Sweden},

abstract = {Humans that negotiate through representatives often instruct those representatives to act in certain ways that align with both the client's goals and his or her social norms. However, which tactics and ethical norms humans endorse vary widely from person to person, and these endorsements may be easy to manipulate. This work presents the results of a study that demonstrates that humans that interact with an artificial agent may change what kinds of tactics and norms they endorse-often dramatically. Previous work has indicated that people that negotiate through artificial agent representatives may be more inclined to fairness than those people that negotiate directly. Our work qualifies that initial picture, demonstrating that subsequent experience may change this tendency toward fairness. By exposing human negotiators to tough, automated agents, we are able to shift the participant's willingness to deceive others and utilize "hard-ball" negotiation techniques. In short, what techniques people decide to endorse is dependent upon their context and experience. We examine the effects of interacting with four different types of automated agents, each with a unique strategy, and how this subsequently changes which strategies a human negotiator might later endorse. In the study, which was conducted on an online negotiation platform, four different types of automated agents negotiate with humans over the course of a 10-minute interaction. The agents differ in a 2x2 design according to agent strategy (tough vs. fair) and agent attitude (nice vs. nasty). These results show that in this multi-issue bargaining task, humans that interacted with a tough agent were more willing to endorse deceptive techniques when instructing their own representative. These kinds of techniques were endorsed even if the agent the human encountered did not use deception as part of its strategy. In contrast to some previous work, there was not a significant effect of agent attitude. These results indicate the power of allowing people to program agents that follow their instructions, but also indicate that these social norms and tactic endorsements may be mutable in the presence of real negotiation experience.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lukin_consequences_2018,

title = {Consequences and Factors of Stylistic Differences in Human-Robot Dialogue},

author = {Stephanie M. Lukin and Kimberly A. Pollard and Claire Bonial and Matthew Marge and Cassidy Henry and Ron Artstein and David Traum and Clare R. Voss},

url = {https://www.aclweb.org/anthology/papers/W/W18/W18-5012/},

doi = {10.18653/v1/W18-5012},

year  = {2018},

date = {2018-07-01},

booktitle = {Proceedings of the SIGDIAL 2018 Conference},

pages = {110–118},

publisher = {Association for Computational Linguistics},

address = {Melbourne, Australia},

abstract = {This paper identifies stylistic differences in instruction-giving observed in a corpus of human-robot dialogue. Differences in verbosity and structure (i.e., single-intent vs. multi-intent instructions) arose naturally without restrictions or prior guidance on how users should speak with the robot. Different styles were found to produce different rates of miscommunication, and correlations were found between style differences and individual user variation, trust, and interaction experience with the robot. Understanding potential consequences and factors that influence style can inform design of dialogue systems that are robust to natural variation from human users.},

keywords = {ARL, DoD, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manuvinakurike_conversational_2018,

title = {Conversational Image Editing: Incremental Intent Identification in a New Dialogue Task},

author = {Ramesh Manuvinakurike and Trung Bui and Walter Chang and Kallirroi Georgila},

url = {https://aclanthology.info/papers/W18-5033/w18-5033},

year  = {2018},

date = {2018-07-01},

booktitle = {Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue},

pages = {284–295},

publisher = {Association for Computational Linguistics},

address = {Melbourne, Australia},

abstract = {We present “conversational image editing”, a novel real-world application domain combining dialogue, visual information, and the use of computer vision. We discuss the importance of dialogue incrementality in this task, and build various models for incremental intent identification based on deep learning and traditional classification algorithms. We show how our model based on convolutional neural networks outperforms models based on random forests, long short term memory networks, and conditional random fields. By training embeddings based on image-related dialogue corpora, we outperform pre-trained out-of-the-box embeddings, for intention identification tasks. Our experiments also provide evidence that incremental intent processing may be more efficient for the user and could save time in accomplishing tasks.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{karkada_towards_2018,

title = {Towards Understanding End-of-trip Instructions in a Taxi Ride Scenario},

author = {Deepthi Karkada and Ramesh Manuvinakurike and Kallirroi Georgila},

url = {https://arxiv.org/abs/1807.03950},

year  = {2018},

date = {2018-07-01},

booktitle = {Proceedings of the Fourteenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation},

publisher = {arxiv.org},

address = {Santa Fe, New Mexico},

abstract = {We introduce a dataset containing human-authored descriptions of target locations in an “end of-trip in a taxi ride” scenario. We describe our data collection method and a novel annotation scheme that supports understanding of such descriptions of target locations. Our dataset contains target location descriptions for both synthetic and real-world images as well as visual annotations (ground truth labels, dimensions of vehicles and objects, coordinates of the target location, distance and direction of the target location from vehicles and objects) that can be used in various visual and language tasks. We also perform a pilot experiment on how the corpus could be applied to visual reference resolution in this domain.},

keywords = {UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}