Language style transfer
Author(s)
Shen, Tianxiao
DownloadFull printable version (351.7Kb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Regina Barzilay.
Terms of use
Metadata
Show full item recordAbstract
This thesis studies style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and attribute modication. The key challenge is to separate the content from style in an unsupervised manner. 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. To demonstrate the flexibility of the proposed model, we test it on three tasks: sentiment modication, decipherment of word substitution ciphers, and word order recovery. In both automatic and human evaluation our method achieves strong performance.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 41-45).
Date issued
2018Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.