The authors show that standard text style-transfer metrics are unstable and manipulable, recommend BLEU against human rewrites as an additional benchmark, and report three architectures that improve on that metric.
Style Transfer Through Multilingual and Feedback-Based Back-Translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
The authors show that standard text style-transfer metrics are unstable and manipulable, recommend BLEU against human rewrites as an additional benchmark, and report three architectures that improve on that metric.