Computational Linguistics Colloquium

Wednesday, December 05, 14:15, DFKI, Room -2.17 (Turing)
NOTE UNUSUAL DAY, TIME, AND PLACE

Ideas on Multi-layer dialogue management for Multi-party, Multi-conversation, Multi-modal communication

Most current dialogue systems concern only a short dialogue between a single system and single user, focused on a single task. On the other hand, the full spectrum of communication between interacting agents includes cases in which multiple segments of conversation can be interleaved with other, sometimes unrelated actions and events (e.g., a cocktail party). The Mission Rehearsal Exercise Project at ICT is between these two extremes, having one main purpose (training relating to decision making in an Army peacekeeping mission), but multiple characters, each with its own goals, interests, and capabilities.

I will present a multiple layer approach towards modelling and managing these complexities, including who is accessible for conversation, paying attention, involved in a conversation, as well as turn-taking, initiative, grounding, and higher-level dialogue functions. The method will follow that used in the Trindi project, where one specifies an information state, and "dialogue moves" representing input and output, as well as associated updates to information state.

A preliminary version of these ideas is presented in this paper.

Brief Biography:

David Traum is a research scientist at Institute for Creative Technologies, and Research Assistant Professor in the computer science department at the University of Southern California. He earned a PhD at University of Rochester in 1994, and has since worked at University of Geneva, Switzerland, and University of Maryland on dialogue modelling, computer-mediated collaboration, and machine translation.

If you would like to meet with the speaker, please contact Malte Gabsdil.