Unsupervised Paraphrasing by Simulated Annealing

Xianggen Liu, Lili Mou, Fandong Meng, Hao Zhou, Jie Zhou, Sen Song


Abstract
We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency of paraphrases. UPSA searches the sentence space towards this objective by performing a sequence of local editing. We evaluate our approach on various datasets, namely, Quora, Wikianswers, MSCOCO, and Twitter. Extensive results show that UPSA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both automatic and human evaluations. Further, our approach outperforms most existing domain-adapted supervised models, showing the generalizability of UPSA.
Anthology ID:
2020.acl-main.28
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
302–312
Language:
URL:
https://aclanthology.org/2020.acl-main.28
DOI:
10.18653/v1/2020.acl-main.28
Bibkey:
Cite (ACL):
Xianggen Liu, Lili Mou, Fandong Meng, Hao Zhou, Jie Zhou, and Sen Song. 2020. Unsupervised Paraphrasing by Simulated Annealing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 302–312, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Paraphrasing by Simulated Annealing (Liu et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.acl-main.28.pdf
Video:
 http://slideslive.com/38928768
Data
COCO