Language Style Transfer from Sentences with Arbitrary Unknown Styles
This addresses the problem of style transfer for natural language processing applications where source styles are unknown and parallel data is unavailable, representing an incremental improvement over existing methods.
The paper tackles language style transfer without parallel data, using a method that encodes sentences into content and style representations and recombines them with a target style, validated on tasks like sentiment modification and Shakespearean rewriting.
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.