Style Transfer from Non-Parallel Text by Cross-Alignment

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.

[1]  John Cocke,et al.  A Statistical Approach to Machine Translation , 1990, CL.

[2]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[3]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[4]  Kevin Knight,et al.  Large Scale Decipherment for Out-of-Domain Machine Translation , 2012, EMNLP-CoNLL.

[5]  Hermann Ney,et al.  Decipherment Complexity in 1: 1 Substitution Ciphers , 2013, ACL.

[6]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[9]  Matt J. Kusner,et al.  GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution , 2016, ArXiv.

[10]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[11]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[12]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Alexander M. Rush,et al.  Word Ordering Without Syntax , 2016, EMNLP.

[14]  Yoshua Bengio,et al.  Professor Forcing: A New Algorithm for Training Recurrent Networks , 2016, NIPS.

[15]  Yoshua Bengio,et al.  Boundary-Seeking Generative Adversarial Networks , 2017, ICLR 2017.

[16]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[17]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[18]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[19]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[20]  Yoshua Bengio,et al.  Maximum-Likelihood Augmented Discrete Generative Adversarial Networks , 2017, ArXiv.

[21]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[22]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[23]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Alexander M. Rush,et al.  OpenNMT: Open-Source Toolkit for Neural Machine Translation , 2017, ACL.

[25]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[26]  Chris Dyer,et al.  Differentiable Scheduled Sampling for Credit Assignment , 2017, ACL.

[27]  Tommi S. Jaakkola,et al.  Sequence to Better Sequence: Continuous Revision of Combinatorial Structures , 2017, ICML.

[28]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[29]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  Eric P. Xing,et al.  Controllable Text Generation , 2017, ArXiv.