A Statistical Model for Discourse Act Recognition in Dialogue Interactions

This paper discusses a statistical model for recognizing discourse intentions of utterances during dialogue interactions. We argue that this recognition process should be based on features of the current utterance as well as on discourse history, and show that taking into account utterance features such as speaker information and syntactic forms of utterances dramatically improves the system’s performance as compared with a simple trigram model of discourse acts. In addition, we propose that taking into account information about discourse structure may allow the system to construct a more accurate discourse act model and thus improve recognition results. Experiments show this proposal to be promising.

[1]  Alex Waibel,et al.  Readings in speech recognition , 1990 .

[2]  Masaaki Nagata,et al.  First steps towards statistical modeling of dialogue to predict the speech act type of the next utterance , 1994, Speech Communication.

[3]  Simon King,et al.  Using prosodic information to constrain language models for spoken dialogue , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  D MooreJohanna,et al.  A problem for RST , 1992 .

[5]  Dan Jurafsky,et al.  Dialog Act Modeling for Conversational Speech , 1998 .

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

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

[8]  Norbert Reithinger.  Some experiments in speech act prediction , 1994 .

[9]  Elmar Nöth,et al.  Automatic classification of dialog acts with semantic classification trees and polygrams , 1995, Learning for Natural Language Processing.

[10]  R. J. Lickley,et al.  Proceedings of the International Conference on Spoken Language Processing. , 1992 .

[11]  Ken Samuel,et al.  Computing Dialogue Acts from Features with Transformation-Based Learning , 1998, ArXiv.

[12]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

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

[14]  J. Cleary,et al.  \self-organized Language Modeling for Speech Recognition". In , 1997 .

[15]  Norbert Reithinger,et al.  Predicting dialogue acts for a speech-to-speech translation system , 1996 .

[16]  Norbert Reithinger,et al.  Dialogue act classification using language models , 1997, EUROSPEECH.

[17]  A. Stolcke,et al.  Dialog act modelling for conversational speech , 1998 .