Speech Dialogue Systems -- A "Pragmatics-First'' Approach to Rational Interaction

The general goal in implementing dialogue systems is in most cases to provide some kind of human-computer-interface for rational interaction. For that purpose, an approach is required which enables such a system to satisfy user goals in a given (ideally open) domain by conducting spoken dialogues. Furthermore, it should be possible to augment it by other kinds of multi-modal interaction like gestures or the selection of items from a menu on a screen. Interactions are called “rational” because rationality principles — at the knowledge representation level — should be applied to optimally select appropriate communicative actions. In this article, different approaches to the understanding of dialogues and the implementation of dialogue systems will be presented. As a basis for comparing the approaches, fundamental issuses of language understanding, speech act theory, and theories of rational interaction are outlined. To give an impression of their implications for the implementation of dialogue systems, we refer to the system framework developed in Erlangen, which has been applied in various projects, as a show case throughout the paper.

[1]  H. Niemann,et al.  An Inference-Based Approach to the Interpretation of Discourse , 2000 .

[2]  Amanda Stent,et al.  Content planning and generation in continuous-speech spoken dialog systems∗ , 2000 .

[3]  Alex Lascarides,et al.  Intentions and information in discourse , 1994 .

[4]  Steven Abney,et al.  Statistical Methods and Linguistics , 2002 .

[5]  Philippe Bretier,et al.  A Rational Agent as the Kernel of a Cooperative Spoken Dialogue System: Implementing a Logical Theory of Interaction , 1996, ATAL.

[6]  David Sadek,et al.  Design Considerations on Dialogue Systems: From Theory to Technology - The Case of Artimis - , 2000 .

[7]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[8]  Astrid Brietzmann,et al.  Pragmatics in Speech Understanding - Revisited , 1982, COLING.

[9]  Nicholas Asher,et al.  Common Ground, Corrections, and Coordination , 2003 .

[10]  Nicholas Asher Discourse Structure and the Logic of Conversation , 2000 .

[11]  R. Cooper,et al.  Information States, Attitudes and Dialogue , 1997 .

[12]  Lynn Lambert,et al.  A Process Model for Recognizing Communicative Acts and Modeling Negotiation Subdialogues , 1999, Comput. Linguistics.

[13]  Andreas Stolcke,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000, CL.

[14]  David R. Traum,et al.  Modelling Grounding and Discourse Obligations Using Update Rules , 2000, ANLP.

[15]  Noam Chomsky,et al.  वाक्यविन्यास का सैद्धान्तिक पक्ष = Aspects of the theory of syntax , 1965 .

[16]  Philip R. Cohen,et al.  Persistence, Intention, and Commitment , 2003 .

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

[18]  A. Lascarides,et al.  Questions in Dialogue , 1998 .

[19]  David R. Traum,et al.  Discourse Obligations in Dialogue Processing , 1994, ACL.

[20]  Steven Abney,et al.  Parsing By Chunks , 1991 .

[21]  Bernd Ludwig,et al.  Ambiguity Reports for Flexible Dialog Management , 2002, PorTAL.

[22]  Areski Nait Abdallah,et al.  The Logic of Partial Information , 1995, Monographs in Theoretical Computer Science An EATCS Series.

[23]  Hector J. Levesque,et al.  GOLOG: A Logic Programming Language for Dynamic Domains , 1997, J. Log. Program..

[24]  Candace L. Sidner,et al.  COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction , 2001, AI Mag..

[25]  Catherine Pelachaud,et al.  Performative facial expressions in animated faces , 2001 .

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

[27]  Jens Allwood,et al.  OBLIGATIONS AND OPTIONS IN DIALOGUE , 1994 .

[28]  Karen Ward,et al.  Integrating multiple cues for spoken language understanding , 1995, CHI 95 Conference Companion.

[29]  S. Toulmin The uses of argument , 1960 .

[30]  Francesco M. Donini,et al.  Reasoning in description logics , 1997 .

[31]  Tomek Strzalkowski,et al.  From Discourse to Logic , 1991 .

[32]  Bernd Ludwig,et al.  Corega Tabs: Incremental Semantic Composition , 2002 .

[33]  Bernd Ludwig,et al.  Corega Tabs: Mapping Semantics onto Pragmatics , 2002 .

[34]  Nathan Griffiths,et al.  Intelligent Agents III: Proceedings of the Third International Workshop on Agent Theories, Architectures and Languages , 1997 .

[35]  M. David Sadek,et al.  A Study in the Logic of Intention , 1992, KR.

[36]  Jens Allwood,et al.  An activity-based approach to pragmatics , 2000, Abduction, Belief and Context in Dialogue.

[37]  Elmar Nöth,et al.  Integrated dialog act segmentation and classification using prosodic features and language models , 1997, EUROSPEECH.

[38]  A. Lascarides,et al.  Cognitive States, Discourse Structure and the Content of Dialogue , 1999 .

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

[40]  David R. Traum,et al.  Representations of Dialogue State for Domain and Task Independent Meta-Dialogue , 1999, Electron. Trans. Artif. Intell..

[41]  Philippe Bretier,et al.  ARTIMIS: Natural Dialogue Meets Rational Agency , 1997, IJCAI.

[42]  Jens Allwood,et al.  Dialog as Collective Thinking , 1997 .

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

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

[45]  Bernd Ludwig,et al.  Using EuroWordNet within the Speech Operated System EMBASSI , 2004, LDV Forum.