An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures(Natural Language Processing)

スポンサーリンク

概要

• 論文の詳細を見る

• Analysis of speech acts and discourse structures is essential to a dialogue understanding system because speech acts and discourse structures are closely tied with the speaker's intention. However, it has been difficult to infer a speech act and a discourse structure from a surface utterance because they highly depend on the context of the utterance. We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using a maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from an annotated dialogue corpus. Moreover, the model can analyze speech acts and discourse structures in one framework. In the experiment, the model showed better performance than other previous works.

• 一般社団法人電子情報通信学会の論文
• 2005-01-01

著者

• Seo Jungyun

  The Dept. Of Computer Science Sogang University

• Choi Won

  Diquest Inc.

• KIM Harksoo

  Diquest Inc.

関連論文

• A Dialogue-Based Information Retrieval Assistant Using Shallow NLP Techniques in Online Sales Domains(Cyberworlds)
• A High Performance Question-Answering System Based on a Two-Pass Answer Indexing and Lexico-Syntactic Pattern Matching(Natural Language Processing)
• An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures(Natural Language Processing)

スポンサーリンク