Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation

Haoran Yang, Wai Lam, Piji Li


Abstract
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal of learning a better representation of the style and the content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.
Anthology ID:
2021.findings-emnlp.409
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4754–4761
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.409
DOI:
10.18653/v1/2021.findings-emnlp.409
Bibkey:
Cite (ACL):
Haoran Yang, Wai Lam, and Piji Li. 2021. Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4754–4761, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation (Yang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.409.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.409.mp4
Code
 lhryang/crl_egpg