Abstract
In this paper, we present a conceptually simple while empirically powerful framework for abstractive summarization, SimCLS, which can bridge the gap between the learning objective and evaluation metrics resulting from the currently dominated sequence-to-sequence learning framework by formulating text generation as a reference-free evaluation problem (i.e., quality estimation) assisted by contrastive learning. Experimental results show that, with minor modification over existing top-scoring systems, SimCLS can improve the performance of existing top-performing models by a large margin. Particularly, 2.51 absolute improvement against BART and 2.50 over PEGASUS w.r.t ROUGE-1 on the CNN/DailyMail dataset, driving the state-of-the-art performance to a new level. We have open-sourced our codes and results: https://github.com/yixinL7/SimCLS. Results of our proposed models have been deployed into ExplainaBoard platform, which allows researchers to understand our systems in a more fine-grained way.- Anthology ID:
- 2021.acl-short.135
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1065–1072
- Language:
- URL:
- https://aclanthology.org/2021.acl-short.135
- DOI:
- 10.18653/v1/2021.acl-short.135
- Cite (ACL):
- Yixin Liu and Pengfei Liu. 2021. SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 1065–1072, Online. Association for Computational Linguistics.
- Cite (Informal):
- SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization (Liu & Liu, ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.acl-short.135.pdf
- Code
- yixinL7/SimCLS + additional community code
- Data
- CNN/Daily Mail, XSum