Structured Content Preservation for Unsupervised Text Style Transfer
This work addresses the challenge of maintaining semantic meaning during style transfer for applications like sentiment modification, though it is incremental in nature.
The paper tackles the problem of content preservation in unsupervised text style transfer by proposing a structured content preserving model that leverages linguistic information and language modeling. The model achieves significant improvements in both content preservation and style transfer performance in sentiment and political slant transfer tasks.
Text style transfer aims to modify the style of a sentence while keeping its content unchanged. Recent style transfer systems often fail to faithfully preserve the content after changing the style. This paper proposes a structured content preserving model that leverages linguistic information in the structured fine-grained supervisions to better preserve the style-independent content during style transfer. In particular, we achieve the goal by devising rich model objectives based on both the sentence's lexical information and a language model that conditions on content. The resulting model therefore is encouraged to retain the semantic meaning of the target sentences. We perform extensive experiments that compare our model to other existing approaches in the tasks of sentiment and political slant transfer. Our model achieves significant improvement in terms of both content preservation and style transfer in automatic and human evaluation.