On Learning Text Style Transfer with Direct Rewards

Cited by: 0|Bibtex|Views11
Other Links: arxiv.org

Abstract:

In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for text style transfer task. In this paper, we explore training algorithms that instead optimize reward functions that explicitly consider different aspects of the style-transferred outputs. In particular, we leverage semantic similarity...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments