Style Transfer from Non-Parallel Text by Cross-Alignment

This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and sentiment modification. The key challenge is to separate the content from other aspects such as style. We assume a shared latent content distribution across different text corpora, and propose a method that leverages refined alignment of latent representations to perform style transfer. The transferred sentences from one style should match example sentences from the other style as a population. We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

PDF Abstract NeurIPS 2017 PDF NeurIPS 2017 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Style Transfer Yelp Review Dataset (Small) CAE G-Score (BLEU, Accuracy) 38.66 # 7

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Unsupervised Text Style Transfer GYAFC CrossAlign [[Shen et al.2017]] BLEU 3.6 # 8
Unsupervised Text Style Transfer Yelp CrossAlign [[Shen et al.2017]] BLEU 17.9 # 9


No methods listed for this paper. Add relevant methods here