TitleA Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
AuthorsWu, Chen
Ren, Xuancheng
Luo, Fuli
Sun, Xu
AffiliationTsinghua Univ, Dept Foreign Languages & Literatures, Beijing, Peoples R China
Tsinghua Univ, MOE Key Lab Computat Linguist, Sch EECS, Beijing, Peoples R China
Peking Univ, Beijing Inst Big Data Res, Ctr Data Sci, Beijing, Peoples R China
Issue Date2019
Publisher57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)
AbstractUnsupervised 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(1).
URIhttp://hdl.handle.net/20.500.11897/552800
IndexedISSHP
CPCI-S(ISTP)
Appears in Collections:待认领

Files in This Work
There are no files associated with this item.

Web of Science®



Checked on Last Week

百度学术™



Checked on Current Time




License: See PKU IR operational policies.