Advanced Topics in Artificial Intelligence (CS 3710 / ISSP 3565)

Spring 2002: Dialog Systems

Time: MW 2:00-3:20  Place: LRDC 814 
Professor:  Dr. Diane Litman Office Hours:  Tu 2:00-4:00 (MIB 214), W 3:30-4:30 & Th 1:15-2:15 (LRDC 741)
Email:  litman@cs.pitt.edu Phone:  412-624-8838 (MIB); 412-624-1261 (LRDC)

Description:

Dialog systems are systems in which human users speak or type to a computer in natural language, in order to achieve their goals. Dialog systems are among the few realized examples of open-ended, real-time, goal-oriented interaction between humans and computers, and are therefore an exciting testbed for artificial intelligence research. Dialog systems are becoming an area of increasing interest, both in research and in practical applications. This course will cover traditional knowledge-based approaches to the problem, more recent statistical work, and fundamental papers both in AI and possibly other disciplines. Topics may include tutoring and call routing applications, spoken dialog systems, spoken translation systems, repair and error recovery, grounding, evaluation, annotation, multi-party dialog analysis (meetings, chat), machine learning approaches, and multi-modal systems, depending on the interests of the registered students.

NOTE: The official course title is "Advanced Topics in Artificial Intelligence." The associated CS and ISSP course numbers are used for many AI graduate seminars. It is okay to take this course more than once, because the topics are different in different years.

Requirements and Grading:

For each class, a student presenter will be assigned to lead the discussion of a set of papers on a given topic. The remaining students will email one or more questions per paper to the presenter, BY 9 AM THE MORNING OF CLASS. These questions should be the kind of questions that you would ask if you heard the contents of the paper in a talk, or were reviewing the paper. The presenter will then email the collection of questions to everyone, which you should read (and print out) before class. The email address of everyone in the class can be found below.

In addition to leading one or more class discussions, all students will be expected to do all the readings, and send the email questions as well as participate in the other discussions.

A project and accompanying paper will also be required of non-auditing students. Project papers are due by class on APRIL 22, which is when oral presentations will begin. A conference paper/presentation is a good model for your project paper and presentation.

Grade Basis: email questions (10%), class participation (10%), leading 2 classes (40%), project or paper (40%)

Prerequisites:

Natural Language Processing, OR a graduate course in Artificial Intelligence, OR consent of the instructor.

Text:

There is no textbook. Students will either download papers from the list of readings, or receive photocopies handed out in advance.

Announcements:

Syllabus (evolving and subject to change):

m

Week Class Topic Readings Presenter Notes
1 Jan 7 Overview and Administration By Friday January 11, please look at the list of readings, and send me an ordered list of topics that you would like to present, as well as any dates that you absolutely cannot lead class. If this constraint satisfaction process proves intractable, I will randomly assign students to topics/dates.    
  Jan 9 No class - instructor away If needed, please pick up the Jan. 14 and 16 readings from the desk outside of LRDC 741. Be sure to email your questions to me before 9 a.m. Monday Jan. 14.    
2 Jan 14 Introduction

Discourse and Dialogue. Grosz, Barbara; Scott, Donia; Kamp, Hans; Cohen, Phil; Giachin, Egidio. Chapter 6 of Discourse and Dialogue: Survey of the State of the Art in Human Language Technology, R. Cole, J. Mariani, H. Uszkoreit, A. Zaenen, & V. Zue (eds.), Cambridge University Press, 1997.

Defining a Conversational Agent. James Allen. Chapter 17 of Natural Language Understanding, Benjamin/Cummings Publishing Company, 1995.

Dialogue and Conversational Agents. Daniel Jurafsky and James H. Martin. Chapter 19 of Speech and Language Processing, Prentice Hall, 2000.

Litman

discussion questions

Jurafsky and Martin notes from Fall NLP class (lec19.ps, lec20.ps)

  Jan 16 Theory

Attention, Intentions, and the Structure of Discourse. Barbara J. Grosz and Candace L. Sidner. Computational Linguistics, 12:3, 1986.

Dialogue Systems. David Sadek and Renato De Mori. Chapter 15 of Spoken Dialogues with Computers, Renato de Mori (ed.), 1998.

Bell

discussion questions

squib arguing for cache model of attentional state

3 Jan 21 University Holiday      
  Jan 23 Theory to Systems

The TRAINS Project. James F. Allen et al. Journal of Experimental and Theoretical AI, 1995.

A Robust System for Natural Spoken Dialogue. James F. Allen, Bradford W. Miller, Eric K. Ringger, and Teresa Sikorski. Proceedings of the Association for Computational Linguistics (ACL), 1996.

ARTIMIS:Natural Dialogue meets Rational Agency. Sadek, P. Bretier, F. Panaget. Proceedings of IJCAI '97, 1997.

Insights into the dialogue processing of Verbmobil. Jan Alexandersson, Norbert Reithinger, and Elisabeth Maier. Proceedings of the Conference on Applied Natural Language Processing (ANLP), 1997.

Roque

discussion questions

TRAINS

TRIPS

Verbmobil

ARTIMIS

4 Jan 28 Systems to Architectures/Toolkits

Smith, D.R. Hipp, and A.W. Biermann. An Architecture for Voice Dialog Systems Based on Prolog-Style Theorem Proving. Computational Linguistics, 21:3, 1995.

An Architecture for a Generic Dialogue Shell. James Allen, Donna Byron, Myroslava Dzikovska, George Ferguson, Lucian Galescu, and Amanda Stent. Natural Language Engineering, 6(3), 2000.

Information state and dialogue management in the TRINDI Dialogue Move Engine Toolkit. Staffan Larsson and David Traum. Natural Language Engineering, 6(3-4), 2000.

Aleven

discussion questions

TRINDI

  Jan 30 No class - instructor away      
5 Feb 4 Dialogue Act Annotation

Coding Dialogs with the DAMSL Annotation Scheme. Mark Core, James Allen. AAAI Fall Symposium on Communicative Action in Humans and Machines, 1997.

Assessing Agreement on Classification Tasks: The Kappa Statistic. Jean Carletta. Computational Linguistics, 22(2):249-254, 1996.

An Empirical Investigation of Proposals in Collaborative Dialogues. Barbara Di Eugenio, Pamela W. Jordan, Johanna D. Moore and Richmond H. Thomason. Proceedings of the 17th International Conference on Computational Linguistics and the 36th Meeting of the Association for Computational Linguistics (COLING-ACL). 1998.

The Reliability of a Dialogue Structure Coding Scheme. Carletta, J. C., Isard, A., Isard, S., Kowtko, J., Doherty-Sneddon, G., & Anderson, A. Computational Linguistics, 23(1), 1997.

Berfield

discussion questions

Coding Schemes

Coconut extension of DAMSL coding scheme

TRAINS 91 Corpus

TRAINS 93 Corpus

Coconut Corpus

Map Task Corpus

  Feb 6 Machine Learning/Statistical Dialogue Act Recognition

Dialogue Act Tagging with Transformation-Based Learning. Ken Samuel, Sandra Carberry, and K. Vijay-Shanker. Proceedings of the 36th Meeting of the Association for Computational Linguistics (ACL), 1998.

Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Marie Meteer, and Carol Van Ess-Dykema. Computational Linguistics 26:3, 2000.

(OPTIONAL: Predicting Dialogue Acts for a Speech-To-Speech Translation System. Norbert Reithinger, Ralf Engel, Michael Kipp, and Martin Klesen. Proceedings of ICSLP, 1996.)

T. Wilson

discussion questions

Switchboard Discourse Language Modelling Project

6 Feb 11 Spoken Dialog: Overview

The Thoughtful Elephant: Strategies for Spoken Dialog Systems. Souvignier, Kellner, Rueber, and Schramm. IEEE Transactions on Speech and Audio Processing, 8:1, 2000.

Jupiter: a Telephone-based Conversational Interface for Weather Information. Zue, Seneff, Glass, Polifroni, Pao, Hazen, and Hetherington. IEEE Transactions on Speech and Audio Processing, 8:1, 2000.

Generating Semantically Consistent Inputs to a Dialog Manager. Abella and Gorin. Proceedings Eurospeech, 1997.

Creating natural dialogs in the Carnegie Mellon Communicator System. Rudnicky, Thayer, Constantinides, Tchou, Shern, Lenzo, Xu, and Oh. Proceedings Eurospeech, 1999.

Gaydos

discussion questions

Spoken Dialogue Systems Tutorial (Carpenter and Chu-Carroll at ACL)

Jupiter and other applications of the MIT Spoken Language Systems Group

How May I Help You?

Darpa Communicator (contains pointers to all the systems, e.g., CMU Communicator)

Let's Talk (BusinessWeek)

  Feb 13 Spoken Dialog: Confidence, Prosody, Repairs

Predicting Automatic Speech Recognition Performance Using Prosodic Cues. Diane Litman, Julia Hirschberg, and Marc Swerts. Proceedings of the First Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL), 2000.

Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech? Elizabeth Shriberg, Rebecca Bates, Paul Taylor, Andreas Stolcke, Daniel Jurafsky, Klaus Ries, Noah Coccaro, Rachel Martin, Marie Meteer, and Carol Van Ess-Dykema. Language and Speech 41:3-4, 1998.

Speech repairs, intonational phrases and discourse markers: modeling speakers' utterances in spoken dialog, Peter Heeman and James Allen. Computational Linguistics, 25(4), 1999.

Bell

discussion questions

TOOT (circa 2000)

Intonational Variation in Spoken Dialogue Systems tutorial and bibliography (Hirschberg)

7 Feb 18 Dialogue Management as Reinforcement Learning

A Stochastic Model of Human Machine Interaction for Learning Dialog Strategies. Esther Levin, Roberto Pieraccini and Wieland Eckert. IEEE Transactions on Speech and Audio Processing, 8:1, 2000.

Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. Satinder Singh, Diane Litman, Michael Kearns and Marilyn Walker. Journal of Artificial Intelligence Research (JAIR), Vol. 16, 2002.

Spoken Dialog Management Using Probabilistic Reasoning. N. Roy, J. Pineau & S. Thrun. Proceedings of the Association for Computational Linguistics (ACL), 2000.

Rotaru

discussion questions

Reinforcement Learning FAQ

Reinforcement Learning textbook

Nursebot.

  Feb 20 Intelligent Tutoring Systems: Corpora

Collaborative dialog patterns in naturalistic one-on-one tutoring. Graesser, A. C., Person, N., & Magliano, J. Applied Cognitive Psychology, 9, 1995.

Learning from human tutoring. Chi, M. T. H., Siler, S., Jeong, H., Yamauchi, T., & Hausmann, R. G. Cognitive Science, 25, 2001.

Modeling Pedagogical Interactions with Machine Learning. Sandra Katz, John Aronis, and Colin Creitz. Artificial Intelligence in Education, 1999.

Modeling Human Teaching Tactics in a Computer Tutor. Mark G. Core, Johanna D. Moore, Claus Zinn and Peter Wiemer-Hastings. Proceedings of the ITS Workshop on Modeling Human Teaching Tactics and Strategies, 2000.

Matsuda

discussion questions

      Project Descriptions Due by February 22 noon.    
8 Feb 25 Intelligent Tutoring Systems: Systems

Intelligent Tutoring Systems with Conversational Dialogue. Arthur Graesser, Kurt VanLehn, Carolyn Rose, Pamela Jordan and Derek Harter. AI Magazine.

Teaching Tactics and Dialog in Autotutor. Arthur C. Graesser, Natalie K. Person, Derek Harter and the Tutoring Research Group. International Journal of Artificial Intelligence in Education, 2001.

Supporting Constructive Learning with a Feedback Planner. M. G. Core, J. D. Moore, and C. Zinn, AAAI Fall Symposium on Building Dialogue Systems for Tutorial Applications, 2000.

Using a Model of Collaborative Dialogue to Teach Procedural Tasks. Jeff Rickel, Neal Lesh, Charles Rich, Candace L. Sidner and Abigail Gertner. Proceedings of 10th International Conference on AI in Education, 2001.

Pilot-Testing a Tutorial Dialogue System that Supports Self-Explanation. Vincent Aleven, Octav Popescu, and Kenneth Koedinger. Submitted.

Lane

discussion questions

Building Dialogue Systems for Tutorial Applications Symposium

AutoTutor (with links to data)

Why2000 and Atlas

Tutorial Dialogue Group at Edinburgh (with links to corpus and coding manuals)

COLLAGEN (particularly TRs 30 and 37)

CIRCSM (particularly MAICS 2001 paper)

  Feb 27 Dialogue Management as Reasoning Under Uncertainty

A Computational Architecture for Conversation. E. Horvitz, T. Paek. Proceedings of the 7th International Conference on User Modeling (UM), 1999.

Conversation as Action Under Uncertainty. T. Paek and E. Horvitz. Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence (UAI), 2000.

DeepListener: Harnessing Expected Utility to Guide Clarification Dialog in Spoken Language Systems. E. Horvitz and T. Paek. Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), 2000.

Continuous Listening for Unconstrained Spoken Dialog. T. Paek, E. Horvitz, E. Ringger. Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), 2000.

Harnessing Models of Users' Goals to Mediate Clarification Dialog in Spoken Language Systems. Eric Horvitz and Tim Paek. Proceedings of the Eighth Conference on User Modeling, 2001.

Williams

discussion questions

Microsoft Conversational Architectures Project

Machine Learning Resources (with links to Bayesian and Belief Network Software)

9 Mar 4 University Holiday      
  Mar 6 University Holiday      
10 Mar 11 Intelligent Tutoring Systems Attend talks during CIRCLE Symposium on Natural Language Tutoring CIRCLE board  
  Mar 13 Evaluation

Empirical Evaluation of User Models and User-Adapted Systems. David Chin. User Modeling and User-Adapted Interaction, 11(1): 2001.

Towards Developing General Models of Usability with PARADISE. Marilyn A. Walker, Diane J. Litman, Candace. A. Kamm and Alicia Abella. Natural Language Engineering, 2000.

Darpa Communicator Dialog Travel Planning Systems: The June 2000 Data Collection. M. Walker, J. Aberdeen, J. Boland, E. Bratt, J. Garofolo, L. Hirschman, A. Le, S. Lee, S. Narayanan, K. Papineni, B. Pellom, J. Polifroni, A. Potamianos, P. Prabhu, A. Rudnicky, G. Sanders, S. Seneff, D. Stallard, S. Whittaker. Proceedings of EUROSPEECH, 2001.

Quantitative and Qualitative Evaluation of Darpa Communicator Spoken Dialogue Systems. Marilyn Walker, Rebecca Passonneau and Julie E. Boland. Proceedings of the Association of Computational Linguistics (ACL), 2001.

(OPTIONAL: Dialogue Strategy Redesign with Reliability Measures. Gies Bouwman and Joris Hulstijn. First International Conference on Language Resources and Evaluation (LREC), 1998.)

Berfield

discussion questions

11 Mar 18 Initiative

Mixed-initiative interaction. IEEE Intelligent Systems, Trends & Controversies, 1999.

Effects of variable initiative on linguistic behavior in human-computer spoken natural language dialog. Ronnie W. Smith and Steven A. Gordon. Computational Linguistics, 23(1), 1997.

An Analysis of Initiative Selection in Collaborative Task-Oriented Discourse (skip Appendices).Curry Guinn. User Modeling and User-Adapted Interaction 8:3-4, 1998.

Exploring Mixed-Initiative Dialogue Using Computer Dialogue Simulation. Masato Ishizaki, Matthew Crocker and Chris Mellish. User Modeling and User-Adapted Interaction 9:1-2, 1999.

Roque

discussion questions

User Modeling and User-Adapted Interaction, Special Issue on Computational Models of Mixed-Initiative Interaction (8:3-4, 9:1-2)

Coding initiative for tutoring (CIRCSIM, Edinburgh)

Classifying Student Initiatives and Tutor Responses in Human Keyboard-to-Keyboard Tutoring Sessions. Farhana Shah and Martha Evens and Joel Michael and Allen Rovick. Discourse Processes 33:1, 2002.

  Mar 20 Adaptive Systems

An evaluation of strategies for selectively verifying utterance meanings in spoken natural language dialog. Ronnie W. Smith. International Journal of Human-Computer Studies 48(5), 1998.

MIMIC: An adaptive mixed initiative spoken dialogue system for information queries. Jennifer Chu-Carroll. Proceedings of the 6th ACL Conference on Applied Natural Language Processing (ANLP), 2000.

Evaluating Automatic Dialogue Strategy Adaptation for a Spoken Dialogue System. J. Chu-Carroll and J. Nickerson. Proceedings of the First Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL), 2000.

Designing and Evaluating an Adaptive Spoken Dialogue System. Diane J. Litman and Shimei Pan. User Modeling and User-Adapted Interaction, to appear.

(OPTIONAL: Recognizing Time Pressure and Cognitive Load on the Basis of Speech: An Experimental Study. Christian Muller, Barbara Grosmann-Hutter, Anthony Jameson, Ralf Rummer, and Frank Wittig, Proceedings of the 8th International Conference of User Modeling (UM), 2001.)

Rotaru

discussion questions

12 Mar 25 Grounding

Contributing to Discourse. H. Clark and E. Schaefer. Cognitive Science 13, 1989.

Beyond Structured Dialogues: Factoring Out Grounding. Peter Heeman, Michael Johnston, Justin Denney and Edward Kaiser. Proceedings of the International Conference on Spoken Language Processing (ICSLP), 1998.

A Psychological Model of Grounding and Repair in Dialog. Janet E. Cahn and Susan E. Brennan. Proceedings of the Fall AAAI Symposium on Psychological Models of Communication in Collaborative Systems, 1999.

Modelling Grounding and Discourse Obligations Using Update Rules. Colin Matheson, Massimo Poesio, and David Traum. Proceedings 1st Meeting of the North American Association for Computational Linguisitcs (NAACL), 2000.

Gaydos

discussion questions

Psychological Models of Communication in Collaborative Systems Symposium

Using Language, Herbert H. Clark, Cambridge University Press, 1996

  Mar 27 Grounding and Reference

Referring as a collaborative process. Clark, Herbert H. and Deanna Wilkes-Gibbs. Cognition 22, 1990. Reprinted in Philip R. Cohen, Jerry Morgan, and Martha E. Pollack, editors, Intentions in Communication, SDF Benchmark Series. MIT Press.

Collaborating on referring expressions. Heeman, Peter A. and Graeme Hirst. Computational Linguistics, 21:3, 1995.

T. Wilson

discussion questions

13 Apr 1 Multi-Party Dialogue Analysis: Collaborative Learning

A Model for Negotiation in Teaching-Learning Dialogues. Michael Baker. International Journal of Artificial Intelligence in Education, 5(2), 1994.

Monitoring Computer-Based Collaborative Problem Solving. Margeret M. McManus and Robert M. Aiken. Journal of Artificial Intelligence in Education, 6(4), 1995.

Modelling Dialogue and Beliefs as a Basis for Generating Guidance in a CSCL Environment. Kristine Lund, Michael Baker and Monique Baron. Proceedings ITS, 1996.

The Tutor's Role: An investigation of the power of Exchange Structure Analysis to identify different roles in CMC seminars. Cornelia Kneser, Rachel Pilkington, and Tamsin Treasure-Jones. International Journal of Artificial Intelligence in Education, Vol. 12, 2001.

Goldin

discussion questions

PSY3485: Learning and Instructional Processes, Michelene T. H. Chi

  Apr 3 Multi-Party Dialogue Analysis: Meetings, Chat

The Meeting Project at ICSI. N. Morgan, D. Baron, J. Edwards, D. Ellis, D. Gelbart, A. Janin, T. Pfau, E. Shriberg, & A. Stolcke. Proceedings First International Conference on Human Language Technology Research (HLT), 2001.

DiaSumm: Flexible Summarization of Spontaneous Dialogues in Unrestricted Domains. Klaus Zechner and Alex Waibel. Proceedings of COLING, 2000.

Seeing eye to eye: an account of grounding and understanding in work groups. Jean Carletta, Anne H. Anderson, and Simon Garrod. Cognitive studies: bulletin of the Japanese Cognitive Science Society, 9(1), 2002.

CobotDS: A Spoken Dialogue System for Chat. Michael Kearns, Charles Isbell, Satinder Singh, Diane Litman, and Jessica Howe. To appear, AAAI 2002.

Soller

discussion questions

The Meeting Recorder Project

Cobot

14 Apr 8 Multimodal Dialogue

Non-Verbal Cues for Discourse Structure. Cassell, J., Nakano, Y., Bickmore, T., Sidner, C., Rich, C. Proceedings of the 41st Annual Meeting of the Association of Computational Linguistics, 2001.

AdApt - a multimodal conversational dialogue system in an apartment domain. Gustafson J, Bell L, Beskow J, Boye J, Carlson R, Edlund J, Granstrom, B, House D & Wiren M. Proc. of ICSLP, 2000.

Toward interface design for human language technology: Modality and structure as determinants of linguistic complexity. Oviatt, S. L., Cohen, P. R. & Wang, M. Q. Speech Communication, European Speech Communication Association, 1994, vol. 15, nos. 3-4, 283-300 (Invited paper for special edition on spoken dialogue, ed. by K. Shirai & S. Furui).

The efficiency of multimodal interaction for a map-based task. Cohen, P. R., McGee, D. R., Clow, J. Proceedings of the Applied Natural Language Processing Conference (ANLP), 2000.

(OPTIONAL: Task-Oriented Collaboration with Embodied Agents in Virtual Worlds. J. Rickel and W.L. Johnson. In J. Cassell, J. Sullivan, S. Prevost, and E. Churchill (Eds.), Embodied Conversational Agents. Boston: MIT Press, 2000.)

Williams

discussion questions

Rea Conversational Humanoid

KTH multimodal dialogue research

QuickSet

Steve

International CLASS Workshop on Natural, Intelligent and Effective Interaction in Multimodal Dialogue Systems

International Conference on Multimodal Interfaces

  Apr 10 Generation

Natural Language Processing and User Modeling: Synergies and Limitations. Ingrid Zukerman and Diane Litman. User Modeling and User Adapted Interaction, Vol 11, 2001.

Collaboration and Student Modeling in Instructional Explanation. Kashihara, A., K. Nomura, T. Hirashima, and J. Toyoda. Proceeedings of the Fifth International Conference on User Modeling (UM), 1996.

Collaborative Response Generation in Planning Dialogues. Chu-Carroll, J. and S. Carberry. Computational Linguistics, Vol 24(3), 1998.

A Trainable Approach to Sentence Planning for Spoken Dialogue. Walker, M. A., O.C Rambow, and Monica Rogati. In submission.

R. Wilson

agenda notes

discussion questions

Siggen (ACL Special Interest Group on Generation)

15 Apr 15 No class - instructor away      
  Apr 17 Argumentation

Designing Electronic Casebooks that Talk Back: The CATO Program. Kevin D. Ashley. Jurimetrics Journal, 2000.

Dialogue Requirements for Argumentation Systems. Richard McConachy and Ingrid Zukerman. Electronic Transactions on Artificial Intelligence (ETAI), Vol. 4, 1999.

ARGUER: Using Argument Schemas for Argument Detection and Rebuttal in Dialogs. A. Restifica, S. Ali, and S. McRoy. Proceedings of the 7th Conference on User Modeling (UM), 1999.

Dialectical Argumentation to Solve Conflicts in Advice Giving. Floriana Grasso, Alison Cawsey and Ray Jones. International Journal of Human-Computer Studies 53(6), 2000.

(OPTIONAL: An Integrated Approach for Generating Arguments and Rebuttals and Understanding Rejoinders. Ingrid Zukerman. Proceedings 8th International Conference on User Modeling (UM), 2001.)

Bruninghaus

discussion questions

Computational Models of Natural Argument Workshops (2002)

16 Apr 22

Project papers due by beginning of class

Project presentations begin (15 minutes each)

Berfield, Roque, Wilson    
  Apr 24 Project presentations continue (15 minutes each) Bell, Gaydos, Rotaru, Williams    

Class Participants and Mailing List:

Name
Vincent Aleven (audit)
Matthew Bell
Alan Berfield
Steffi Bruninghaus (audit)
Andy Gaydos
Ilya Goldin (audit)
H. Chad Lane (audit)
Diane Litman (professor)
Noboru Matsuda (audit)
Antonio Roque
Mihai Rotaru
Amy Soller (audit)
Eric Williams
Roy Wilson (audit)
Theresa Wilson

Useful or Interesting Links:

ACL SIGdial

Special Issue on Intelligent Dialogue Systems for the ETAI area Intelligent User Interfaces

Related courses at CMU, more CMU, OGI, another OGI, Chicago, Goteborgs, Eindhoven, MIT, and Texas.

Entertainment Dialog Engine

Resources for Projects:

Pointers to corpora (e.g. Coconut, Trains, Map Task, Switchboard, AutoTutor, Basic Electricity & Electronics) can be found with the relevant readings. Some have annotations, some don't. Other corpora that are available for projects include TOOT, NJFun data (available from me), CIRCLE archive dialogues, CU Communicator dialogues, SRI's Amex Travel Agent Data, and perhaps Miss Lindquist (particularly if you are interested in Reinforcement Learning). Your own data would be great too.

Pointers to toolkits (e.g. TRINDI) can be found with the relevant readings. Other tools that are available for projects include CSLU toolkit, CSLR Communicator, Tellme, and SRI Open Agent Architecture.

Pointers to machine learning software can be found with the relevant readings. Or download TiMBL: Tilburg Memory Based Learner (version 4.1). Also see UCI Machine Learning Repository and Machine Learning Resources for more pointers, or see me for pointers to ML software already installed at Pitt. For unsupervised learning, try Self- Organizing Maps.

TextTiling Software is available for automatically performing high-level discourse segmentation of a corpus.