Abstract
This study addresses the problem of automatically detecting decisions in conversational speech. We formulate the problem as classifying decision-making units at two levels of granularity: dialogue acts and topic segments. We conduct an empirical analysis to determine the characteristic features of decision-making dialogue acts, and trainMaxEnt models using these features for the classification tasks. We find that models that combine lexical, prosodic, contextual and topical features yield the best results on both tasks, achieving 72% and 86% precision, respectively. The study also provides a quantitative analysis of the relative importance of the feature types.
Original language | English |
---|---|
Title of host publication | Proceedings of the Annual conference of the North American Chapter of the Association for Computational Linguistics 2007 (NAACL-HLT) |
Publisher | Association for Computational Linguistics |
Pages | 25-32 |
Number of pages | 8 |
Publication status | Published - Apr 2007 |