Style Transfer Through Back-Translation
This work addresses the problem of automated text style transfer for applications like content adaptation, but it is incremental as it builds on existing translation and adversarial methods.
The paper tackled style transfer in text by introducing a method that uses a latent representation from a language translation model to preserve meaning and adversarial generation to match style, achieving improvements in automatic and manual evaluations on sentiment, gender, and political slant transformations compared to state-of-the-art techniques.
Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context. This paper introduces a new method for automatic style transfer. We first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties. Then adversarial generation techniques are used to make the output match the desired style. We evaluate this technique on three different style transformations: sentiment, gender and political slant. Compared to two state-of-the-art style transfer modeling techniques we show improvements both in automatic evaluation of style transfer and in manual evaluation of meaning preservation and fluency.