SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization

Yixin Liu, Pengfei Liu
2021 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Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)   unpublished
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 topscoring
more » ... s, SimCLS can improve the performance of existing top-performing models by a large margin. Particularly, 2.51 absolute improvement against BART (Lewis et al., 2020) and 2.50 over PEGASUS (Zhang et al., 2020a) 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 EX-PLAINABOARD (Liu et al., 2021a) platform, which allows researchers to understand our systems in a more fine-grained way.
doi:10.18653/v1/2021.acl-short.135 fatcat:br6444mjifewtcyfrzotzmfa2a