@InProceedings{gervits2018lrec, author={Felix Gervits and Matthias Scheutz}, title={Towards a Conversation-Analytic Taxonomy of Speech Overlap}, booktitle={Proceedings of the 11th edition of the Language Resources and Evaluation Conference (LREC)}, year={2018}, projects={itl,social,team}, topics={dia,comm}, image={gervits2018lrec.jpg}, synopsis={We present a taxonomy for classifying speech overlap in natural language dialogue. We describe the various dimensions of this scheme and show how it was applied to a corpus of remote dialogue.}, }

@InProceedings{gervitsetal2017aiaa, author={Felix Gervits and Charlotte Warne and Harrison Downs and Kathleen Eberhard and Matthias Scheutz}, title={Exploring Coordination in Human-Robot Teams in Space}, booktitle={Proceedings of the American Institute of Aeronautics and Astronautics (AIAA) Space Forum}, year={2017}, projects={team,social}, topics={hri,dia,comm,mixed}, image={gervitsetal2017aiaa.jpg}, synopsis={We introduce a novel experimental paradigm to study human-robot teaming in a space domain. The platform is unique in that it is scalable and customizable to various team configurations, allowing for the study of various dimensions of teaming within the same task domain.}, }

@InProceedings{gervitsetal2017cogsci, author={Felix Gervits and Gordon Briggs and Matthias Scheutz}, title={The Pragmatic Parliament: A Framework for Socially-Appropriate Utterance Selection in Artificial Agents}, booktitle={Proceedings of the 39th Annual Meeting of the Cognitive Science Society}, year={2017}, projects={cm,social}, topics={prag,hri,comm}, presentation={}, synopsis={We introduce a framework for natural language generation in artificial agents that is sensitive to a variety of social and communicative goals. We show how these goals can be ranked and fused by use of a voting algorithm to modulate directive generation in various domains.}, }

@InProceedings{gervits2017pioneers, author = {Felix Gervits}, title = {Disfluency Handling for Robot Teammates}, booktitle = {Proceedings of the Human-Robot Interaction (HRI) Pioneers Workshop}, year = {2017}, projects={team,social}, topics={dia,comm,hri}, presentation={gervits2017pioneers.pdf}, synopsis={I report on my empirical work which shows that effective human teams produced about twice as many self-repair disfluencies as ineffective teams in a collaborative search task. I then describe ongoing work to implement disfluency-handling mechanisms for robots that serve on teams with humans.}, }

@Article{gervitsetal2016frontiers, title={Team Communication as a Collaborative Process}, author={Felix Gervits and Kathleen Eberhard and Matthias Scheutz}, journal={Frontiers in Robotics and AI}, volume={3}, pages={62}, year={2016}, projects={team,itl}, topics={dia,comm,mixed}, synopsis={We report on the results of a corpus analysis aimed at exploring the various factors that influence communication and performance in a collaborative search task. We found that effective teams used specific communication strategies to improve coordination and to establish and maintain common ground, and that these strategies were affected by task constraints. A number of other linguistic- and dialogue-level features were also found to be influenced by factors such as time pressure, speaker role, and team effectiveness.}, }

@InProceedings{gervitsetal2016coling, author={Felix Gervits and Kathleen Eberhard and Matthias Scheutz}, title={Disfluent but effective? A quantitative study of disfluencies and conversational moves in team discourse}, booktitle={Proceedings of the 26th International Conference on Computational Linguistics}, year={2016}, projects={team,social}, topics={hri,dia,comm,mixed}, presentation={gervitsetal2016coling.odp}, synopsis={We examine empirical data on grounding strategies and the use of disfluency in team discourse, and find that these abilities are crucial for team coordination and performance. We discuss how artificial agents can benefit from being able to handle and generate these dialogue features for more natural and effective interaction.}, }