A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer

Chen Wu, Xuancheng Ren, Fuli Luo, Xu Sun


Abstract
Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) the transfer is weakly interpretable, 2) generated outputs struggle in content preservation, and 3) the trade-off between content and style is intractable. To address these challenges, we propose a hierarchical reinforced sequence operation method, named Point-Then-Operate (PTO), which consists of a high-level agent that proposes operation positions and a low-level agent that alters the sentence. We provide comprehensive training objectives to control the fluency, style, and content of the outputs and a mask-based inference algorithm that allows for multi-step revision based on the single-step trained agents. Experimental results on two text style transfer datasets show that our method significantly outperforms recent methods and effectively addresses the aforementioned challenges.
Anthology ID:
P19-1482
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4873–4883
Language:
URL:
https://aclanthology.org/P19-1482
DOI:
10.18653/v1/P19-1482
Bibkey:
Cite (ACL):
Chen Wu, Xuancheng Ren, Fuli Luo, and Xu Sun. 2019. A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4873–4883, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer (Wu et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/P19-1482.pdf
Video:
 https://vimeo.com/385265051