Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
This addresses the challenge of generating sentiment-altered text while preserving content for natural language processing applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackled the problem of sentiment-to-sentiment translation without parallel data by proposing a cycled reinforcement learning method, resulting in significant improvements in content preservation with BLEU scores increasing from 1.64 to 22.46 and 0.56 to 14.06 on Yelp and Amazon datasets.
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.