Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management

Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management Zhengxu Hou author Bang Liu author Ruihui Zhao author Zijing Ou author Yafei Liu author Xi Chen author Yefeng Zheng author 2021-06 text Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Kristina Toutanova editor Anna Rumshisky editor Luke Zettlemoyer editor Dilek Hakkani-Tur editor Iz Beltagy editor Steven Bethard editor Ryan Cotterell editor Tanmoy Chakraborty editor Yichao Zhou editor Association for Computational Linguistics Online conference publication hou-etal-2021-imperfect 10.18653/v1/2021.naacl-main.238 https://aclanthology.org/2021.naacl-main.238/ 2021-06 2993 3001