https://scholars.lib.ntu.edu.tw/handle/123456789/559426
標題: | Discriminative deep Dyna-Q: Robust planning for dialogue policy learning | 作者: | Su, S.-Y. Li, X. Gao, J. Liu, J. YUN-NUNG CHEN |
公開日期: | 2020 | 起(迄)頁: | 3813-3823 | 來源出版物: | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 | 摘要: | This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested.1 © 2018 Association for Computational Linguistics |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85062083317&partnerID=40&md5=f4397ee8a77a664510b0b84cbf926754 https://scholars.lib.ntu.edu.tw/handle/123456789/559426 |
SDG/關鍵字: | Deep learning; Natural language processing systems; User experience; Changing environment; Domain extensions; Policy learning; Q algorithms; Robust planning; Training data; Quality control |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。