A user simulator architecture for socially-aware conversational agents

Alankar Jain, Florian Pecune, Yoichi Matsuyama, Justine Cassell

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

Over the last two decades, Reinforcement Learning (RL) has emerged the method of choice for data-driven dialog management. However, one of the limitations of RL methods for the optimization of dialog managers in the context of virtual conversational agents, is that they require a large amount of data, which is often unavailable, particularly when the dialog deals with complex discourse phenomena. User simulators help address this problem by generating synthetic data to train RL agents in an online fashion. In this work, we extend user simulators to the case of socially-aware conversational agents, that combine task and social functions. We propose a novel architecture that takes into consideration the user’s conversational goals and generates both task and social behaviour. Our proposed architecture is general enough to be useful for training socially-aware conversational agents in any domain. As a proof of concept, we construct a user simulator for training a conversational recommendation agent and provide evidence towards the effectiveness of the approach.

本文言語English
ホスト出版物のタイトルProceedings of the 18th International Conference on Intelligent Virtual Agents, IVA 2018
出版社Association for Computing Machinery, Inc
ページ133-140
ページ数8
ISBN(電子版)9781450360135
DOI
出版ステータスPublished - 2018 11月 5
外部発表はい
イベント18th ACM International Conference on Intelligent Virtual Agents, IVA 2018 - Sydney, Australia
継続期間: 2018 11月 52018 11月 8

出版物シリーズ

名前Proceedings of the 18th International Conference on Intelligent Virtual Agents, IVA 2018

Conference

Conference18th ACM International Conference on Intelligent Virtual Agents, IVA 2018
国/地域Australia
CitySydney
Period18/11/518/11/8

ASJC Scopus subject areas

  • 人工知能
  • 人間とコンピュータの相互作用

フィンガープリント

「A user simulator architecture for socially-aware conversational agents」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