Style Transfer from Non-Parallel Text by Cross-Alignment
Style Transfer from Non-Parallel Text by Cross-Alignment
复制标题
DOI：
--
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
T. Shen;Tao Lei;R. Barzilay;T. Jaakkola
中科院分区：
文献类型：
--
作者：
T. Shen;Tao Lei;R. Barzilay;T. Jaakkola
本文以非平行语篇为研究对象，研究语体迁移问题。这是一系列问题中的一个例子，包括机器翻译、破译和情感修改。关键的挑战是将内容与风格等其他方面分开。我们假设在不同的文本语料库中共享潜在内容分布，并提出了一种利用潜在表示的精细化对齐来执行样式迁移的方法。从一种文体转移的句子应该与另一种文体的例句作为总体匹配。我们在三个任务上验证了这种交叉对齐方法的有效性：情感修正、单词替换密码的破译和词序的恢复。
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.