首页    期刊浏览 2024年11月26日 星期二
登录注册

文章基本信息

  • 标题:人狼ゲームにおける対話システムのための中間表現および自然言語から中間表現への変換
  • 本地全文:下载
  • 作者:箕輪 峻 ; 狩野 芳伸
  • 期刊名称:人工知能学会論文誌
  • 印刷版ISSN:1346-0714
  • 电子版ISSN:1346-8030
  • 出版年度:2020
  • 卷号:35
  • 期号:1
  • 页码:1-13
  • DOI:10.1527/tjsai.DSI-F
  • 出版社:The Japanese Society for Artificial Intelligence
  • 摘要:

    Recently, end-to-end learning is frequently used to implement dialogue systems. However, existing systems still suffer from issues to handle complex dialogues. In this paper, we target on the conversation game “Mafia”, which requires players to make consistent and complex communications. We propose a middle language expression and a converter from natural language input. We implemented our dialogue system to play the Mafia game with humans and other automatic agents. Our evaluation on the play shows that our middle language increases conversion coverage.

  • 关键词:dialog system;game player agent;inter-language;AI werewolf
国家哲学社会科学文献中心版权所有