Style transfer from non-parallel text by cross-alignment
Name
7259-style-transfer-from-non-parallel-text-by-cross-alignment.pdf
Description
Published version
Size
342.38 KB
Format
Adobe PDF
Checksum (MD5)
fb4988305e976509df2cc7042c1ff65a
Author(s)
Jaakkola, Tommi
Barzilay, Regina
Lei, Tao
Shen, Tianxiao
Date Issued
2017
Citation
Jaakkola, Tommi, Barzilay, Regina, Lei, Tao and Shen, Tianxiao. 2017. "Style transfer from non-parallel text by cross-alignment."
Version
Final published version
Abstract
© 2017 Neural information processing systems foundation. All rights reserved. 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7259-style-transfer-from-non-parallel-text-by-cross-alignment
