Dialogue Systems as Conversational Partners: Applying Conversation Acts Theory to Natural Language G

When people talk with computers, they interact very differently from how they interact in conversation with other people. Some of these differences come from people’s adapting to limitations in the computer’s abilities to interact naturally. If we can make computers interact in a more realistic way, we can reduce the cognitive load on users of dialogue systems. In this dissertation, we explore how to design generation systems that can not only produce coherent, informative and responsive dialogue contributions, but also explicitly model human styles of interaction. This exploration includes two approaches. First, we report on the in-depth analysis of a corpus of human-human task-oriented dialogues, the Monroe corpus. We use this analysis to examine the relative contributions of the different levels of conversation acts: turn-taking, grounding, speech acts and argumentation acts. We also examine the effect of initiative and dialogue levels on task-oriented conversation. Second, we describe a computational model of generation based on conversation acts theory. This model has been implemented in a generation system for the TRIPS system at the University of Rochester. The generation system is flexible and efficient. It includes components to plan dialogue contributions, perform surface generation for different media, and coordinate output production. We discuss our implementation, and describe an evaluation of the model.

[1]  Johanna D. Moore,et al.  Toward a Synthesis of Two Accounts of Discourse Structure , 1996, CL.

[2]  James F. Allen,et al.  Applying Genetic Algorithms to Pronoun Resolution , 1999, AAAI/IAAI.

[3]  Mikio Nakano,et al.  Handling rich turn-taking in spoken dialogue systems , 1999, EUROSPEECH.

[4]  Srinivas Bangalore,et al.  Evaluation Metrics for Generation , 2000, INLG.

[5]  John L. Arnott,et al.  Studies of Turn-Taking in Computer-Mediated Communication , 1994, Interact. Comput..

[6]  Stuart M. Shieber,et al.  Synchronous Tree-Adjoining Grammars , 1990, COLING.

[7]  James F. Allen,et al.  Dialogue Transcription Tools , 1995 .

[8]  Michael Elhadad,et al.  An Overview of SURGE: a Reusable Comprehensive Syntactic Realization Component , 1996, INLG.

[9]  Donald W. Fiske,et al.  Face-to-face interaction: Research, methods, and theory , 1977 .

[10]  James F. Allen,et al.  An architecture for a generic dialogue shell , 2000, Natural Language Engineering.

[11]  Kevin Knight,et al.  Generation that Exploits Corpus-Based Statistical Knowledge , 1998, ACL.

[12]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

[13]  Ronnie W. Smith,et al.  Effects of Variable Initiative on Linguistic Behavior in Human-Computer Spoken Natural Language Dialogue , 1997, Comput. Linguistics.

[14]  J. Austin.  How to do things with words , 1962 .

[15]  James F. Allen,et al.  Hierarchical statistical language models: experiments on in-domain adaptation , 2000, INTERSPEECH.

[16]  Marilyn A. Walker,et al.  Evaluating spoken dialogue agents with PARADISE: Two case studies , 1998, Comput. Speech Lang..

[17]  Lynn Lambert,et al.  A Tripartite Plan-Based Model of Dialogue , 1991, ACL.

[18]  David R. Traum,et al.  A Two-level Approach to Coding Dialogue for Discourse Structure: Activities of the 1998 DRI Working Group on Higher-level Structures , 1999 .

[19]  Alexander I. Rudnicky,et al.  Expanding the Scope of the ATIS Task: The ATIS-3 Corpus , 1994, HLT.

[20]  Steven K. Feiner,et al.  Automating the generation of coordinated multimedia explanations , 1991, Computer.

[21]  Thomas Rist,et al.  The Design of Illustrated Documents as a Planning Task , 1993, AAAI Workshop on Intelligent Multimedia Interfaces.

[22]  Scott McGlashan,et al.  Generating Utterances in Dialogue Systems , 1992, NLG.

[23]  Srinivas Bangalore,et al.  Corpus-Based Lexical Choice in Natural Language Generation , 2000, ACL.

[24]  Sharon L. Oviatt,et al.  Integration themes in multimodal human-computer interaction , 1994, ICSLP.

[25]  Jill House,et al.  Evaluating the prosody of synthesized utterances within a dialogue system , 1992, ICSLP.

[26]  Kathleen F. McCoy,et al.  A Functional Approach to Generation with TAG , 1992, ACL.

[27]  Clifford Nass,et al.  Computers are social actors , 1994, CHI '94.

[28]  J. J. Garcia-Luna-Aceves,et al.  Floor control for multimedia conferencing and collaboration , 1997, Multimedia Systems.

[29]  Hector J. Levesque,et al.  Rational interaction as the basis for communication , 2003 .

[30]  David R. Traum,et al.  Conversational Actions and Discourse Situations , 1997, Comput. Intell..

[31]  Wolfgang Finkler,et al.  Incremental generation for real-time applications , 1995 .

[32]  Lance A. Ramshaw.  A Three-Level Model for Plan Exploration , 1991, ACL.

[33]  Jennifer Chu-Carroll,et al.  Collaborative Response Generation in Planning Dialogues , 1998, Comput. Linguistics.

[34]  David G. Novick,et al.  What is Mixed-Initiative Interaction? , 1997 .

[35]  Thomas Rist,et al.  Planning Referential Acts for Animated Presentation Agents , 1997 .

[36]  Amanda Stent,et al.  TRAINS-96 System Evaluation , 1997 .

[37]  Scott Axelrod.  Natural Language Generation in the IBM Flight Information System , 2000 .

[38]  J. Searle.  Expression and Meaning: A taxonomy of illocutionary acts , 1975 .

[39]  Johanna D. Moore,et al.  Saying it in graphics: from intentions to visualizations , 1998, Proceedings IEEE Symposium on Information Visualization (Cat. No.98TB100258).

[40]  Gwyneth Doherty-Sneddon,et al.  The Reliability of a Dialogue Structure Coding Scheme , 1997, CL.

[41]  K..  Tracking Initiative in Collaborative Dialogue Interactions , 2002 .

[42]  Eduard H. Hovy,et al.  Automated Discourse Generation Using Discourse Structure Relations , 1993, Artif. Intell..

[43]  Johanna D. Moore,et al.  An Empirical Investigation of Proposals in Collaborative Dialogues , 1998, ACL.

[44]  K. Chang,et al.  Embodiment in conversational interfaces: Rea , 1999, CHI '99.

[45]  Kathleen R. McKeown,et al.  Natural language generation in COMET , 1990 .

[46]  James F. Allen,et al.  Toward Conversational Human-Computer Interaction , 2001, AI Mag..

[47]  M. Knapp,et al.  Turn-Taking in Conversations. , 1975 .

[48]  Juntae Yoon,et al.  A Feature-Based Lexicalized Tree Adjoining Grammar for Korean , 2000 .

[49]  Alexander I. Rudnicky,et al.  Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[50]  William C. Mann,et al.  RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION , 1987 .

[51]  William E. Hefley,et al.  Intelligent Multimedia Presentation Systems: Research and Principles , 1991, AAAI Workshop on Intelligent Multimedia Interfaces.

[52]  and K R McKeown,et al.  LANGUAGE GENERATION AND EXPLANATION , 1987 .

[53]  Johanna D. Moore,et al.  A Problem for RST: The Need for Multi-Level Discourse Analysis , 1992, CL.

[54]  Kathleen F. McCoy,et al.  Generating Anaphoric Expressions: Pronoun or Definite Description? , 1999 .

[55]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[56]  Jennifer Chu-Carroll,et al.  Generating Information-Sharing Subdialogues in Expert-User Consultation , 1995, IJCAI.

[57]  E. Schegloff,et al.  A simplest systematics for the organization of turn-taking for conversation , 1974 .

[58]  Marilyn A. Walker,et al.  Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation , 1990, ACL.

[59]  Alexander I. Rudnicky,et al.  Creating natural dialogs in the carnegie mellon communicator system , 1999, EUROSPEECH.

[60]  Stephanie Seneff,et al.  GENESIS-II: a versatile system for language generation in conversational system applications , 2000, INTERSPEECH.

[61]  Owen Rambow,et al.  Tree adjoining grammars : formalisms, linguistic analysis, and processing , 2000 .

[62]  Johanna D. Moore,et al.  Planning Text for Advisory Dialogues: Capturing Intentional and Rhetorical Information , 1993, CL.

[63]  Mark G. Core,et al.  Coding Dialogs with the DAMSL Annotation Scheme , 1997 .

[64]  Timothy W. Finin,et al.  A Proposal for a new KQML Specification , 1997 .

[65]  David McKelvie,et al.  The MATE workbench - An annotation tool for XML coded speech corpora , 2001, Speech Commun..

[66]  Herbert H. Clark,et al.  Contributing to Discourse , 1989, Cogn. Sci..

[67]  Robert Dale,et al.  Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions , 1995, Cogn. Sci..

[68]  Ana Paiva,et al.  Heroes, villians, magicians, …: dramatis personae in a virtual story creation environment , 2001, IUI '01.

[69]  Aravind K. Joshi,et al.  An Earley-Type Parsing Algorithm for Tree Adjoining Grammars , 1988, ACL.

[70]  James F. Allen,et al.  The TRAINS 93 Dialogues , 1995 .

[71]  Ronnie W. Smith,et al.  Effective Spoken Natural Language Dialog Requires Variable Initiative Behavior: An Empirical Study , 1993 .

[72]  David G. Novick,et al.  Coordinating turn-taking with gaze , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[73]  James F. Allen,et al.  Towards Conversational Human-Computer Interaction , 2000 .

[74]  Steve Whittaker,et al.  Cues and control in Expert-Client Dialogues , 1988, ACL.

[75]  Alexander I. Rudnicky,et al.  Dialog analysis in the carnegie mellon communicator , 1999, EUROSPEECH.

[76]  James F. Allen,et al.  An architecture for more realistic conversational systems , 2001, IUI '01.

[77]  D. Marcu,et al.  Experiments in Constructing a Corpus of Discourse Trees : Problems , Annotation Choices , Issues , 1999 .

[78]  Staffan Larsson,et al.  Information state and dialogue management in the TRINDI dialogue move engine toolkit , 2000, Natural Language Engineering.

[79]  Aravind K. Joshi,et al.  Tree-Adjoining Grammars , 1997, Handbook of Formal Languages.

[80]  Susan E. Brennan,et al.  LEXICAL ENTRAINMENT IN SPONTANEOUS DIALOG , 1996 .

[81]  Matthew Stone,et al.  Sentence Planning as Description Using Tree Adjoining Grammar , 1997, ACL.

[82]  Aravind K. Joshi,et al.  Feature Structures Based Tree Adjoining Grammars , 1988, COLING.

[83]  Michael K. Brown,et al.  Initiative in Collaborative Interactions m Its Cues and Effects , 1997 .

[84]  James F. Allen,et al.  A Task-Based Evaluation of the TRAINS-95 Dialogue System , 1996, ECAI Workshop on Dialogue Processing in Spoken Language Systems.

[85]  Songsak Channarukul,et al.  A Natural Language Generation Component for Dialog Systems , 1999 .

[86]  Michael Elhadad,et al.  Controlling Content Realization with Functional Unification Grammars , 1992, NLG.

[87]  C. Sidner,et al.  Plans for Discourse , 1988 .

[88]  James C. Lester,et al.  Developing and Empirically Evaluating Robust Explanation Generators: The KNIGHT Experiments , 1997, Comput. Linguistics.

[89]  Victor Zue,et al.  Empirical evaluation of human performance and agreement in parsing discourse constituents in spoken dialogue , 1995, EUROSPEECH.

[90]  Wolfgang Wahlster,et al.  Plan-Based Integration of Natural Language and Graphics Generation , 1993, Artif. Intell..

[91]  Aravind K. Joshi,et al.  Tree Adjunct Grammars , 1975, J. Comput. Syst. Sci..

[92]  Marilyn A. Walker,et al.  Evaluating Response Strategies in a Web-Based Spoken Dialogue Agent , 1998, ACL.

[93]  Barbara Di Eugenio,et al.  Control and Initiative in Collaborative Problem Solving Dialogues , 1997 .

[94]  Joakim Gustafson,et al.  Interaction with an animated agent in a spoken dialogue system , 1999, EUROSPEECH.

[95]  P R Cohen,et al.  The role of voice input for human-machine communication. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[96]  Shimei Pan,et al.  Spoken language generation in a multimedia system , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[97]  Jean-Yves Antoine,et al.  Obtaining Predictive Results with an Objective Evaluation of Spoken Dialogue Systems: Experiments with the DCR Assessment Paradigm , 2000, LREC.

[98]  Alexander I. Rudnicky,et al.  Multi-Site Data Collection and Evaluation in Spoken Language Understanding , 1993, HLT.

[99]  D. O’connell,et al.  Turn-taking: A critical analysis of the research tradition , 1990 .

[100]  Amanda Stent,et al.  The CommandTalk Spoken Dialogue System , 1999, ACL.

[101]  Thomas Rist,et al.  Coping with Temporal Constraints in Multimedia Presentation Planning , 1996, AAAI/IAAI, Vol. 1.

[102]  Toby Donaldson.  Addressing User Misconceptions within a Goal-oriented, Turn-taking Framework in Dialogue Time-bounded Persistent Goals Background Adopting and Dropping Goals , 1996 .

[103]  George R. Doddington,et al.  The ATIS Spoken Language Systems Pilot Corpus , 1990, HLT.

[104]  Clive Souter,et al.  Dialogue Management Systems: a Survey and Overview , 1997 .

[105]  Shimei Pan,et al.  Empirically Evaluating an Adaptable Spoken Dialogue System , 1999, ArXiv.