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.
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.
@inproceedings{yamshchikov-etal-2019-decomposing,
title = "Decomposing Textual Information For Style Transfer",
author = {Yamshchikov, Ivan P. and
Shibaev, Viacheslav and
Nagaev, Aleksander and
Jost, J{\"u}rgen and
Tikhonov, Alexey},
editor = "Birch, Alexandra and
Finch, Andrew and
Hayashi, Hiroaki and
Konstas, Ioannis and
Luong, Thang and
Neubig, Graham and
Oda, Yusuke and
Sudoh, Katsuhito",
booktitle = "Proceedings of the 3rd Workshop on Neural Generation and Translation",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5613/",
doi = "10.18653/v1/D19-5613",
pages = "128--137",
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."
}
%0 Conference Proceedings
%T Decomposing Textual Information For Style Transfer
%A Yamshchikov, Ivan P.
%A Shibaev, Viacheslav
%A Nagaev, Aleksander
%A Jost, Jürgen
%A Tikhonov, Alexey
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Hayashi, Hiroaki
%Y Konstas, Ioannis
%Y Luong, Thang
%Y Neubig, Graham
%Y Oda, Yusuke
%Y Sudoh, Katsuhito
%S Proceedings of the 3rd Workshop on Neural Generation and Translation
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F yamshchikov-etal-2019-decomposing
%X 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.
%R 10.18653/v1/D19-5613
%U https://aclanthology.org/D19-5613/
%U https://doi.org/10.18653/v1/D19-5613
%P 128-137
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.