Style Transfer from Non-Parallel Text by Cross-Alignment

Code

• github.com/shentianxiao/language-style-transfer
  OfficialIn papertf★ 0
• github.com/kyuer/language-style-transfer
  tf★ 0
• github.com/bywords/lang-style-transfer-legacy
  tf★ 0
• github.com/qfzhu/st
  tf★ 0
• github.com/sy-sunmoon/Clever-Commenter-Let-s-Try-More-Apps
  pytorch★ 0
• github.com/jishavm/TextStyleTransfer
  tf★ 0
• github.com/mariob6/style_text
  pytorch★ 0
• github.com/nlahlaf/Text-Style-Transfer
  tf★ 0
• github.com/kaletap/nlp-style-transfer
  tf★ 0
• github.com/jpark621/language-style-transfer
  tf★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions