Timezone: »

 
Poster
Style Transfer from Non-Parallel Text by Cross-Alignment
Tianxiao Shen · Tao Lei · Regina Barzilay · Tommi Jaakkola

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #94 #None
in Posters Wed »

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.

Keywords: Representation Learning · Natural Language Processing · Adversarial Networks

Author Information

Tianxiao Shen (MIT)
Tao Lei (MIT)
Regina Barzilay (Massachusetts Institute of Technology)
Tommi Jaakkola (MIT)

Tommi Jaakkola is a professor of Electrical Engineering and Computer Science at MIT. He received an M.Sc. degree in theoretical physics from Helsinki University of Technology, and Ph.D. from MIT in computational neuroscience. Following a Sloan postdoctoral fellowship in computational molecular biology, he joined the MIT faculty in 1998. His research interests include statistical inference, graphical models, and large scale modern estimation problems with predominantly incomplete data.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors