Probabilistic Head-Driven Parsing for Discourse Structure

We describe a data-driven approach to building interpretable discourse structures for appointment scheduling dialogues. We represent discourse structures as headed trees and model them with probabilistic head-driven parsing techniques. We show that dialogue-based features regarding turn-taking and domain specific goals have a large positive impact on performance. Our best model achieves an f-score of 43.2% for labelled discourse relations and 67.9% for unlabelled ones, significantly beating a right-branching baseline that uses the most frequent relations.

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

[2]  Michael Strube,et al.  A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue , 2003, ACL.

[3]  A. Lascarides,et al.  Resolving Fragments using Discourse Information , 2002 .

[4]  Alex Lascarides,et al.  Logics of Conversation , 2005, Studies in natural language processing.

[5]  Renata Vieira,et al.  Corpus-based Development and Evaluation of a System for Processing Definite Descriptions , 2000, COLING.

[6]  Janyce Wiebe,et al.  An Empirical Approach to Temporal Reference Resolution , 1997, EMNLP.

[7]  Jan van Eijck,et al.  Representing Discourse in Context , 1997, Handbook of Logic and Language.

[8]  Daniel Marcu,et al.  A Decision-Based Approach to Rhetorical Parsing , 1999, ACL.

[9]  Daniel Marcu,et al.  Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory , 2001, SIGDIAL Workshop.

[10]  Stephan Oepen,et al.  LinGO Redwoods , 2004 .

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

[12]  G. Meade.  Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory , 2001 .

[13]  Rashmi Prasad,et al.  The Penn Discourse Treebank , 2004, LREC.

[14]  Daniel Marcu.  The rhetorical parsing of natural language texts , 1997 .

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

[16]  Renata Vieira,et al.  Processing definite descriptions in corpora , 2000 .

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

[18]  William C. Mann,et al.  Rhetorical Structure Theory: Description and Construction of Text Structures , 1987 .