Statistical Dialogue Management using Intention Dependency Graph

Koichiro Yoshino, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

We present a method of statistical dialogue management using a directed intention dependency graph (IDG) in a partially observable Markov decision process (POMDP) framework. The transition probabilities in this model involve information derived from a hierarchical graph of intentions. In this way, we combine the deterministic graph structure of a conventional rule-based system with a statistical dialogue framework. The IDG also provides a reasonable constraint on a user simulation model, which is used when learning a policy function in POMDP and dialogue evaluation. Thus, this method converts a conventional dialogue manager to a statistical dialogue manager that utilizes task domain knowledge without annotated dialogue data.

本文言語English
ホスト出版物のタイトル6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference
編集者Ruslan Mitkov, Jong C. Park
出版社Asian Federation of Natural Language Processing
ページ962-966
ページ数5
ISBN(電子版)9784990734800
出版ステータスPublished - 2013
外部発表はい
イベント6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Nagoya, Japan
継続期間: 2013 10月 14 → …

出版物シリーズ

名前6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference

Conference

Conference6th International Joint Conference on Natural Language Processing, IJCNLP 2013
国/地域Japan
CityNagoya
Period13/10/14 → …

ASJC Scopus subject areas

  • 人工知能
  • ソフトウェア

フィンガープリント

「Statistical Dialogue Management using Intention Dependency Graph」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル