Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach

Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, Wenjie Li


Abstract
The goal of sentiment-to-sentiment “translation” is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To solve this problem, we propose a cycled reinforcement learning method that enables training on unpaired data by collaboration between a neutralization module and an emotionalization module. We evaluate our approach on two review datasets, Yelp and Amazon. Experimental results show that our approach significantly outperforms the state-of-the-art systems. Especially, the proposed method substantially improves the content preservation performance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to 14.06 on the two datasets, respectively.
Anthology ID:
P18-1090
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
979–988
Language:
URL:
https://aclanthology.org/P18-1090
DOI:
10.18653/v1/P18-1090
Bibkey:
Cite (ACL):
Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, and Wenjie Li. 2018. Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 979–988, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach (Xu et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1090.pdf
Presentation:
 P18-1090.Presentation.pdf
Video:
 https://aclanthology.org/P18-1090.mp4
Code
 lancopku/unpaired-sentiment-translation
Data
GYAFCYelp