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

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.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract


Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Unsupervised Text Style Transfer GYAFC Unpaired [[Xu et al.2018]] BLEU 2.0 # 9
Unsupervised Text Style Transfer Yelp Unpaired [[Xu et al.2018]] BLEU 37.0 # 6


No methods listed for this paper. Add relevant methods here