Ryuichi Takanobu, Hanlin Zhu, Minlie Huang. Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog. In Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan 0001, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019. pages 100-110, Association for Computational Linguistics, 2019. [doi]
@inproceedings{TakanobuZH19,
title = {Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog},
author = {Ryuichi Takanobu and Hanlin Zhu and Minlie Huang},
year = {2019},
doi = {10.18653/v1/D19-1010},
url = {https://doi.org/10.18653/v1/D19-1010},
researchr = {https://researchr.org/publication/TakanobuZH19},
cites = {0},
citedby = {0},
pages = {100-110},
booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019},
editor = {Kentaro Inui and Jing Jiang and Vincent Ng and Xiaojun Wan 0001},
publisher = {Association for Computational Linguistics},
isbn = {978-1-950737-90-1},
}