Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer

Chulun Zhou, Liangyu Chen, Jiachen Liu, Xinyan Xiao, Jinsong Su, Sheng Guo, Hua Wu


Abstract
Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style, they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.
Anthology ID:
2020.acl-main.639
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7135–7144
Language:
URL:
https://aclanthology.org/2020.acl-main.639
DOI:
10.18653/v1/2020.acl-main.639
Bibkey:
Cite (ACL):
Chulun Zhou, Liangyu Chen, Jiachen Liu, Xinyan Xiao, Jinsong Su, Sheng Guo, and Hua Wu. 2020. Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7135–7144, Online. Association for Computational Linguistics.
Cite (Informal):
Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer (Zhou et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.639.pdf
Video:
 http://slideslive.com/38928938
Code
 PaddlePaddle/Research
Data
GYAFC