Hierarchy Response Learning for Neural Conversation Generation

Bo Zhang, Xiaoming Zhang


Abstract
The neural encoder-decoder models have shown great promise in neural conversation generation. However, they cannot perceive and express the intention effectively, and hence often generate dull and generic responses. Unlike past work that has focused on diversifying the output at word-level or discourse-level with a flat model to alleviate this problem, we propose a hierarchical generation model to capture the different levels of diversity using the conditional variational autoencoders. Specifically, a hierarchical response generation (HRG) framework is proposed to capture the conversation intention in a natural and coherent way. It has two modules, namely, an expression reconstruction model to capture the hierarchical correlation between expression and intention, and an expression attention model to effectively combine the expressions with contents. Finally, the training procedure of HRG is improved by introducing reconstruction loss. Experiment results show that our model can generate the responses with more appropriate content and expression.
Anthology ID:
D19-1186
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1772–1781
Language:
URL:
https://aclanthology.org/D19-1186
DOI:
10.18653/v1/D19-1186
Bibkey:
Cite (ACL):
Bo Zhang and Xiaoming Zhang. 2019. Hierarchy Response Learning for Neural Conversation Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1772–1781, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Hierarchy Response Learning for Neural Conversation Generation (Zhang & Zhang, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1186.pdf