Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/89106
PIRA download icon_1.1View/Download Full Text
Title: Unpaired sentiment-to-sentiment translation : a cycled reinforcement learning approach
Authors: Xu, J
Sun, X
Zeng, Q
Ren, X
Zhang, X
Wang, H
Li, W 
Issue Date: 2018
Source: In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15-20 July 2018, (Vol. 1: Long Papers) , p. 979-988. Stroudsburg : Association for Computational Linguistics, 2018.
Abstract: The goal of sentiment-to-sentiment “translation” is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To solve this problem, we propose a cycled reinforcement learning method that enables training on unpaired data by collaboration between a neutralization module and an emotionalization module. We evaluate our approach on two review datasets, Yelp and Amazon. Experimental results show that our approach significantly outperforms the state-of-the-art systems. Especially, the proposed method substantially improves the content preservation performance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to 14.06 on the two datasets, respectively.
Publisher: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/p18-1090
Rights: © 2017 Association for Computational Linguistics
ACL materials are Copyright © 1963–2021 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/).
The following publication Xu, J., Sun, X., Zeng, Q., Ren, X., Zhang, X., Wang, H., & Li, W. (2018). Unpaired sentiment-to-sentiment translation: A cycled reinforcement learning approach. Paper presented at the ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 1, 979-988 is available at https://dx.doi.org/10.18653/v1/p18-1090
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
P18-1090.pdf423.06 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

22
Citations as of Jul 3, 2022

SCOPUSTM   
Citations

74
Citations as of Jun 30, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.