SentiInc: Incorporating Sentiment Information into Sentiment Transfer Without Parallel Data

Sentiment-to-sentiment transfer involves changing the sentiment of the given text while preserving the underlying information. In this work, we present a model SentiInc for sentiment-to-sentiment transfer using unpaired mono-sentiment data. Existing sentiment-to-sentiment transfer models ignore the valuable sentiment-specific details already present in the text. We address this issue by providing a simple framework for encoding sentiment-specific information in the target sentence while preserving the content information. This is done by incorporating sentiment based loss in the back-translation based style transfer. Extensive experiments over the Yelp dataset show that the SentiInc outperforms state-of-the-art methods by a margin of as large as equation ~11% in G-score. The results also demonstrate that our model produces sentiment-accurate and information-preserved sentences.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Text Style Transfer Yelp Review Dataset (Large) SentiInc G-Score (BLEU, Accuracy) 59.17 # 1
Text Style Transfer Yelp Review Dataset (Small) SentiInc G-Score (BLEU, Accuracy) 66.25 # 2

Methods


No methods listed for this paper. Add relevant methods here