Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders

Zhangming Chan, Juntao Li, Xiaopeng Yang, Xiuying Chen, Wenpeng Hu, Dongyan Zhao, Rui Yan


Abstract
Variational autoencoders (VAEs) and Wasserstein autoencoders (WAEs) have achieved noticeable progress in open-domain response generation. Through introducing latent variables in continuous space, these models are capable of capturing utterance-level semantics, e.g., topic, syntactic properties, and thus can generate informative and diversified responses. In this work, we improve the WAE for response generation. In addition to the utterance-level information, we also model user-level information in latent continue space. Specifically, we embed user-level and utterance-level information into two multimodal distributions, and combine these two multimodal distributions into a mixed distribution. This mixed distribution will be used as the prior distribution of WAE in our proposed model, named as PersonaWAE. Experimental results on a large-scale real-world dataset confirm the superiority of our model for generating informative and personalized responses, where both automatic and human evaluations outperform state-of-the-art models.
Anthology ID:
D19-1201
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:
1931–1940
Language:
URL:
https://aclanthology.org/D19-1201
DOI:
10.18653/v1/D19-1201
Bibkey:
Cite (ACL):
Zhangming Chan, Juntao Li, Xiaopeng Yang, Xiuying Chen, Wenpeng Hu, Dongyan Zhao, and Rui Yan. 2019. Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders. 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 1931–1940, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders (Chan et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/D19-1201.pdf