Conversational agents are becoming increasingly used for various tasks, domains, and settings (e.g., personal assistants, customer service agents, intelligent tutors, and more), driven by recent advances in artificial intelligence and natural language processing. One major interaction benefit of conversational interfaces is the ability to dynamically generate contents and adapt to individual users. However, such personified designs of conversational agents often lead to advanced user expectations regarding the system’s sensing and adaptive capabilities. Users expect such agents to not only satisfy their individual information needs, but to also behave in socially appropriate or favorable ways.
Therefore, conversational agent systems present an extremely rich and challenging research space for addressing many aspects of user awareness and adaptation, such as user profiles, contexts, personalities, emotions, social dynamics, conversational styles, etc. Adaptive interfaces are a long-standing interest for the HCI community, which has often made extensive efforts to study users, and prototype, evaluate, and design adaptive actions of computing systems. However, these efforts are sometimes isolated from the challenges of developing the sensing capabilities of systems, and the opportunities of leveraging data-driven approaches and computational intelligence.
Meanwhile, increasingly more advanced machine learning approaches are introduced in new generations of conversational agents, such as deep learning, reinforcement learning, and active learning. It is imperative to consider how various aspects of user-awareness should be handled by these new techniques and system components for language understanding, language generation, dialog management, and in settings of end-to-end conversation modeling.
The goal of this workshop is to bring together researchers in HCI, user modeling, and the AI and NLP communities from both industry and academia, who are interested in advancing the state-of-the-art on the topic of user-aware conversational agents. Through a focused and open exchange of ideas and discussions, we will work to identify central research topics in user-aware conversational agents and develop a strong interdisciplinary foundation to address them. With its focus on the intersection of HCI and AI communities, we strongly believe IUI is an ideal venue in which to hold this workshop.
- The workshop solicits submissions in all aspects of user-aware and adaptive conversational agents including:
- User modeling for conversational agents and multi-modal interactions
- Sensing capabilities of agents (e.g., emotion, personality, contexts, social dynamic, etc.)
- Agent adaptation through language generation, dialog management and conversation modeling
- Personalization and adaptation algorithms inspired by behavioral or psychological theories
- Adapting agent interactions for user engagement
- Transparency and control of adaptive agents
- Novel methods for evaluating adaptive agents
- User interactions with and perceptions of adaptive agents
- Case studies of adaptive agents for different uses cases (e.g. collaborative tasks, decision support, social agent) and different domains (e.g. healthcare, finance, education)
This will be a half-day workshop including keynote speakers, papers, posters, and discussion sessions. Discussion sessions will focus on enumerating key challenges in user-aware conversational agents and developing an interdisciplinary research agenda.
Based on the results of the workshop, we plan to organize a special journal issue of the ACM Transactions on Interactive Intelligent Systems (TIIS) on this topic.
IUI-user2agent encourages original and relevant work of two publication types:
- full papers (up to 10 pages), including work in progress, perspective papers, and lessons learned. They will be presented either as oral presentations or posters.
- position papers (up to 4 pages), which will be presented as posters with a possibility to be accompanied by a demo.
All papers should follow ACM SIGCHI templates: https://sigchi.org/templates/, and submitted electronically as a single PDF file through the EasyChair submission system: https://easychair.org/conferences/?conf=user2agent.
All submissions will undergo a peer-review process. Reviewers will consider originality, significance, technical soundness, clarity, and relevance to the workshop’s topics. The reviewing process will be double-blind.
- Yasaman Khazaeni,
IBM Research AI, Cambridge Research Lab, USA
- Q. Vera Liao,
IBM Research AI, TJ Watson Research Center, USA
- Michal Shmueli-Scheuer,
IBM Research AI, Haifa Research Lab, Israel
- Tsung-Hsien (Shawn) Wen,
- Zhou Yu,
University of California, Davis, USA
- Mari Ostendorf, University of Washington
- Alex Rudnicky, CMU
- Marilyn Walker, University of California, Santa Cruz
- Michelle X. Zhou, Juji.io
- Yun-Nung (Vivian) Chen, National Taiwan University
- Adam Fourney, Microsoft Research
- Jonathan Herzig, Tel-Aviv University
- Tianran Hu, University of Rochester
- Kenneth Huang, Pennsylvania State University
- Bernd Huber, Harvard University
- Werner Geyer, IBM Research AI
- Stefan Kopp, Bielefeld University
- Yukiko Nakano, Seikei University
- Ameneh Shamekhi, Northeastern University
- Tanmay Sinha, ETH Zurich
- Eddy Su, PolyAI
- Stefan Ultes, University of Cambridge
- Rajan Vaish, Snap Research
|Submission deadline:||December 14, 2018|
|Notifications to authors:||January 14, 2019|
|Camera-ready of accepted papers:||February 15, 2019|
|Workshop date:||March 20, 2019|