Style Transfer from Non-Parallel Text by Cross-Alignment
This addresses style transfer for text processing applications, but it appears incremental as it builds on existing alignment and latent representation methods.
The paper tackled style transfer from non-parallel text by separating content from style using a shared latent content distribution and cross-alignment of latent representations, achieving effectiveness in tasks like sentiment modification, decipherment, and word order recovery.
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.