Decomposing Textual Information For Style Transfer

Ivan P. Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, Jürgen Jost, Alexey Tikhonov


Abstract
This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations.
Anthology ID:
D19-5613
Volume:
Proceedings of the 3rd Workshop on Neural Generation and Translation
Month:
November
Year:
2019
Address:
Hong Kong
Editors:
Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Ioannis Konstas, Thang Luong, Graham Neubig, Yusuke Oda, Katsuhito Sudoh
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
128–137
Language:
URL:
https://aclanthology.org/D19-5613
DOI:
10.18653/v1/D19-5613
Bibkey:
Cite (ACL):
Ivan P. Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, Jürgen Jost, and Alexey Tikhonov. 2019. Decomposing Textual Information For Style Transfer. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 128–137, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Decomposing Textual Information For Style Transfer (Yamshchikov et al., NGT 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5613.pdf