Language Style Transfer from Non-Parallel Text with Arbitrary Styles

Language style transfer is the problem of migrating the content of a source sentence to a target style. In many applications, parallel training data are not available and source sentences to be transferred may have arbitrary and unknown styles. In this paper, we present an encoder-decoder framework under this problem setting. Each sentence is encoded into its content and style latent representations. By recombining the content with the target style, we can 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 proposed model on two tasks: sentiment modification of restaurant reviews, and dialog response revision with a romantic style.