Balancing Lexical and Semantic Quality in Abstractive Summarization

2Citations
Citations of this article
18Readers
Mendeley users who have this article in their library.

Abstract

An important problem of the sequence-to-sequence neural models widely used in abstractive summarization is exposure bias. To alleviate this problem, re-ranking systems have been applied in recent years. Despite some performance improvements, this approach remains underexplored. Previous works have mostly specified the rank through the ROUGE score and aligned candidate summaries, but there can be quite a large gap between the lexical overlap metric and semantic similarity. In this paper, we propose a novel training method in which a re-ranker balances the lexical and semantic quality. We further newly define false positives in ranking and present a strategy to reduce their influence. Experiments on the CNN/DailyMail and XSum datasets show that our method can estimate the meaning of summaries without seriously degrading the lexical aspect. More specifically, it achieves an 89.67 BERTScore on the CNN/DailyMail dataset, reaching new state-of-the-art performance. Our code is publicly available at https://github.com/jeewoo1025/BalSum.

Cite

CITATION STYLE

APA

Sul, J., & Choi, Y. S. (2023). Balancing Lexical and Semantic Quality in Abstractive Summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (Vol. 2, pp. 637–647). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.acl-short.56

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free