2021/06/03 by Yixin Liu, Pengfei Liu, Liu, Yixin +1 · 11 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial intelligence #Automatic summarization #Bridge (graph theory) #Computer science #Machine learning #Margin (machine learning) #Natural Language Processing Techniques #Natural language processing #Quality (philosophy) #Sequence (biology) #Simple (philosophy) #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2106.01890
published in arXiv (Cornell University) (Cornell University) · Published as a short paper at ACL 2021
arxiv created 2021/06/03 · openalex publication_date 2021/06/03 · arxiv updated 2021/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.