Many interactive systems strive to afford the same mechanisms to human users that are used in face-to-face conversation. This course examines the formal models and computational techniques that concern the pragmatics of language use that such systems employ.
Expanded course description below
For a course with complementary material, see COSC6328.3 Speech and Language Processing
Auditors are welcome.
The schedule below will be subject to frequent revisions.
Papers to be presented by students are marked with an asterisk (*)
|
Lecture |
Topic |
Readings |
Presenter |
|
Lecture 1 |
Course Intro and Overview | ||
|
Lectures 2-5 |
Module 1: Elemental Constructs |
Ch. 18-19, Jurafsky and Martin, 2000. | Instructor |
|
Lectures 6-9 |
Module 2: Structure of Text |
(*)Barbara Grosz and Julia Hirschberg Some intonational characteristics of discourse. Proceeding of the ICSLP, 1992.[PS] | Tsirlin |
|
(*)Jane Morris and Graeme Hirst Lexical Cohesion Computed by Thesaural Relations as an Indicator of the Structure of Text . Computational Linguistics 17(1), pp. 21-48, 1991.[PDF] | Vazquez-Abrams | ||
|
(*)Marti Hearst Multi-paragraph segmentation of expository text Proceedings of the ACL, pp. 9-16, 1994.[PDF] | Dadgari | ||
|
(*)Daniel Marcu Building Up Rhetorical Structure Trees Proceeding of the AAAI, 1996[PDF] |
Tam | ||
|
Lectures 10-12 |
Module 3: Structure of Conversation |
Overview | Instructor |
|
(*)Paek, T and Horvitz, E. Conversation as Action Under Uncertainty. In
Proceedings of the 16th Conference on Uncertainty in
Artificial Intelligence (UAI-2000), 2000. pp. 455-464.[PDF] | Zaman | ||
|
(*)Michel Galley, Kathleen McKeown, Eric Fosler-Lussier and Hongyan Jing Discourse Segmentation of Multi-Party Conversation Proceedings of the ACL, 2003.[PDF] | Instructor | ||
|
Lectures 13-15 |
Module 4: Structure of quasi-conversational exchanges |
||
|
Tues, Feb 28 (*)D. J. Litman, M. A. Walker and M. S. Kearns Automatic Detection of Poor Speech Recognition at the Dialogue Level Proceedings of ACL, 1999[PDF] | Instructor | ||
|
Thurs, Mar 2 (*)A. L. Gorin, G. Riccardi and J. H. Wright. How May I Help You? Speech Communication, 23 (1/2), 113-127, 1997[PDF] (access required via York Library eResources) | Phillips | ||
|
Lectures 16-18 |
Module 5: Pragmatics of Embodiment |
Tues, Mar 7 Overview (Readings, if any, TBA) | Instructor |
|
Thurs, Mar 9 (*)Cassell, J. Embodied Conversational Interface Agents. Communications of the ACM, 43(4):70-78, 2000.[PDF] (access required via York Library eResources) | Gill | ||
|
Tues, Mar 14 (*)Yukiko Nakano; Gabe Reinstein; Tom Stocky; Justine Cassell. Toward a Model of Face-to-Face Grounding. Proceedings of ACL, 2003. [PDF] | Hu | ||
|
Lectures 19-21 |
Module 6: Human Acquisition of Pragmatic Processes |
Thurs, Mar 16 Overview (Readings, if any, TBA) | Instructor |
|
Tues, Mar 21 (*)J Siskind. A Computational Study of Cross-Situational Techniques for Learning Word-to-Meaning Mappings. [PDF] | Ramay | ||
|
Thurs, Mar 23 (*)P Gorniak, D Roy. Grounded semantic composition for visual scenes. Journal of Artificial Intelligence Research, 2004[PDF] | Instructor | ||
|
Lectures 22-24 |
Module 7: Communication Disorders |
Tues, Mar 28 Overview (Readings, if any, TBA) | Instructor |
|
Thurs, Mar 30 (*)Todman and Alm. Modelling conversational pragmatics in communication aids. Journal of Pragmatics, 35(4):523-538, 2003.[PDF] (access required via York Library eResources) | Kulikov | ||
|
Tues, Apr 4 (*)KF McCoy, CA Pennington, A Luberoff Badman. Compansion: From research prototype to practical integration. Natural Language Engineering, 4(1):73-95, 2000[PDF] | tbd | ||
Conversational exchanges are also characterized by the use of multiple modes (such as speech, gaze, gestures of the head and hands, and facial expression). Many interactive systems afford their users the opportunity to use these modes as well. A special class of interactive systems, embodied communicative agents or ECAs, make use of lifesize humanoid animated agents which are also capable of making use of these modes in order to communicate with their human users. This course introduces the main formal frameworks for distinguishing among modes of communication and examines the computational techniques for the automatic interpretation of multimodal user actions and the automatic generation of multimodal system actions.
Systems that have been designed to afford interactions that are conversational in nature are often touted as more natural, use-friendly, effecient, effective, and intuitive. This course examines the primary methods of evaluation that have been applied in the research community.
The primary mode of inquiry for this course will be the examination of exemplar interactive systems. The accomplishments and limitations of the existing models and techniques will be presented and open research problems will be discussed.