Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/89106
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 | Size | Format | |
---|---|---|---|---|
P18-1090.pdf | 423.06 kB | Adobe PDF | View/Open |
Page views
36
Last Week
1
1
Last month
Citations as of May 28, 2023
Downloads
3
Citations as of May 28, 2023
SCOPUSTM
Citations
103
Citations as of May 25, 2023

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