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

By Jingjing Xu, Xu Sun, Qi Zeng, Xuancheng Ren, Xiaodong Zhang, Houfeng Wang, Wenjie Li. 2018

215 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Reinforcement Learning, Sentiment & Opinion Analysis, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Mohit Bansal
  3. Percy Liang
  4. Yejin Choi
  5. Luke S. Zettlemoyer
  6. Graham Neubig
  7. Noah A. Smith
  8. Yoshua Bengio

In Reinforcement Learning

  1. Ludovic Denoyer
  2. Jie Zhou
  3. Lawrence Carin
  4. Peng Li
  5. Xiujun Li
  6. Xu Sun
  7. Jianze Liang
  8. Ning Dai

In Sentiment & Opinion Analysis

  1. Xu Sun
  2. Rada Mihalcea
  3. Xuancheng Ren
  4. Junyang Lin
  5. Jingjing Xu

In Natural Language Generation

  1. Mohit Iyyer
  2. John Wieting
  3. Houfeng Wang
  4. Jianfeng Gao
  5. Zhifang Sui
  6. Baobao Chang
  7. Jie Zhou
  8. Sandeep Subramanian

Citations in the corpus