Language Style Transfer from Sentences with Arbitrary Unknown Styles
arXiv:1808.04071
Abstract
Language style transfer is the problem of migrating the content of a source sentence to a target style. In many of its applications, parallel training data are not available and source sentences to be transferred may have arbitrary and unknown styles. First, each sentence is encoded into its content and style latent representations. Then, by recombining the content with the target style, we decode a sentence aligned in the target domain. To adequately constrain the encoding and decoding functions, we couple them with two loss functions. The first is a style discrepancy loss, enforcing that the style representation accurately encodes the style information guided by the discrepancy between the sentence style and the target style. The second is a cycle consistency loss, which ensures that the transferred sentence should preserve the content of the original sentence disentangled from its style. We validate the effectiveness of our model in three tasks: sentiment modification of restaurant reviews, dialog response revision with a romantic style, and sentence rewriting with a Shakespearean style.
References in corpus (13)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- A Deep Reinforced Model for Abstractive Summarization
- Deep Convolutional Inverse Graphics Network
- Style Transfer from Non-Parallel Text by Cross-Alignment
- Dual Learning for Machine Translation
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Toward Controlled Generation of Text
- Deep Photo Style Transfer
- From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots
- Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
- Style Transfer in Text: Exploration and Evaluation