Incremental Parsing Models for Dialog Task Structure

In this paper, we present an integrated model of the two central tasks of dialog management: interpreting user actions and generating system actions. We model the interpretation task as a classification problem and the generation task as a prediction problem. These two tasks are interleaved in an incremental parsing-based dialog model. We compare three alternative parsing methods for this dialog model using a corpus of human-human spoken dialog from a catalog ordering domain that has been annotated for dialog acts and task/subtask information. We contrast the amount of context provided by each method and its impact on performance.

[1]  Barbara Di Eugenio,et al.  FLSA: Extending Latent Semantic Analysis with Features for Dialogue Act Classification , 2004, ACL.

[2]  Massimo Poesio,et al.  The predictive power of game structure in dialogue act recognition: experimental results using maximum entropy estimation , 1998, ICSLP.

[3]  Nate Blaylock,et al.  Hierarchical Instantiated Goal Recognition , 2006 .

[4]  Christopher Culy,et al.  Sentential Structure and Discourse Parsing , 2004, ACL 2004.

[5]  Martin van den Berg,et al.  A Rule Based Approach to Discourse Parsing , 2004, SIGDIAL Workshop.

[6]  Daniel Marcu,et al.  Sentence Level Discourse Parsing using Syntactic and Lexical Information , 2003, NAACL.

[7]  Hung Hai Bui,et al.  A General Model for Online Probabilistic Plan Recognition , 2003, IJCAI.

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

[9]  James F. Allen,et al.  A Plan Recognition Model for Subdialogues in Conversations , 1987, Cogn. Sci..

[10]  Giovanni Soda,et al.  Wide Coverage Incremental Parsing by Learning Attachment Preferences , 2001, AI*IA.

[11]  Ralph Grishman,et al.  Evaluating syntax performance of parser/grammars , 1991 .

[12]  Karen E. Lochbaum,et al.  A Collaborative Planning Model of Intentional Structure , 1998, CL.

[13]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[14]  Christian R. Huyck,et al.  Generating discourse structures for written texts , 2004, COLING 2004.

[15]  Alex Lascarides,et al.  Combining Hierarchical Clustering and Machine Learning to Predict High-Level Discourse Structure , 2004, COLING.

[16]  James F. Allen,et al.  A Plan Recognition Model for Subdialogues in Conversations , 1987, Cogn. Sci..

[17]  Sandra Carberry,et al.  Techniques for Plan Recognition , 2001, User Modeling and User-Adapted Interaction.

[18]  Adwait Ratnaparkhi,et al.  A Linear Observed Time Statistical Parser Based on Maximum Entropy Models , 1997, EMNLP.

[19]  Alon Lavie,et al.  A Best-First Probabilistic Shift-Reduce Parser , 2006, ACL.

[20]  Anthony Barrett,et al.  Task-Decomposition via Plan Parsing , 1994, AAAI.

[21]  Norbert Reithinger,et al.  Learning dialogue structures from a corpus , 1997, EUROSPEECH.

[22]  Michael P. Wellman,et al.  Probabilistic State-Dependent Grammars for Plan Recognition , 2000, UAI.

[23]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[24]  Bonnie L. Webber,et al.  D-LTAG System: Discourse Parsing with a Lexicalized Tree-Adjoining Grammar , 2003, J. Log. Lang. Inf..

[25]  Patrick Haffner,et al.  Scaling large margin classifiers for spoken language understanding , 2006, Speech Commun..

[26]  Alexander I. Rudnicky,et al.  Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda , 2003, INTERSPEECH.

[27]  Jason Baldridge,et al.  Probabilistic Head-Driven Parsing for Discourse Structure , 2005, CoNLL.

[28]  Dan Cristea.  An Incremental Discourse Parser Architecture , 2000, Natural Language Processing.

[29]  Joakim Nivre,et al.  Discriminative Classifiers for Deterministic Dependency Parsing , 2006, ACL.

[30]  Candace L. Sidner,et al.  COLLAGEN: when agents collaborate with people , 1997, AGENTS '97.

[31]  Candace L. Sidner,et al.  Plan parsing for intended response recognition in discourse 1 , 1985, Comput. Intell..