Style Transfer Through Multilingual and Feedback-Based Back-Translation
This work addresses the problem of balancing meaning preservation and style accuracy in text style transfer, which is incremental as it builds on existing models.
The paper tackled the challenge of meaning preservation in style transfer by proposing two extensions to state-of-the-art models, resulting in improved grounding of meaning and enhanced transfer accuracy.
Style transfer is the task of transferring an attribute of a sentence (e.g., formality) while maintaining its semantic content. The key challenge in style transfer is to strike a balance between the competing goals, one to preserve meaning and the other to improve the style transfer accuracy. Prior research has identified that the task of meaning preservation is generally harder to attain and evaluate. This paper proposes two extensions of the state-of-the-art style transfer models aiming at improving the meaning preservation in style transfer. Our evaluation shows that these extensions help to ground meaning better while improving the transfer accuracy.