Improving Factual Consistency in Summarization with Compression-Based Post-Editing

Alex Fabbri, Prafulla Kumar Choubey, Jesse Vig, Chien-Sheng Wu, Caiming Xiong


Abstract
State-of-the-art summarization models still struggle to be factually consistent with the input text. A model-agnostic way to address this problem is post-editing the generated summaries. However, existing approaches typically fail to remove entity errors if a suitable input entity replacement is not available or may insert erroneous content. In our work, we focus on removing extrinsic entity errors, or entities not in the source, to improve consistency while retaining the summary’s essential information and form. We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed. We show that this model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and that this model can be applied on top of another post-editor, improving entity precision by up to a total of 38%. We perform an extensive comparison of post-editing approaches that demonstrate trade-offs between factual consistency, informativeness, and grammaticality, and we analyze settings where post-editors show the largest improvements.
Anthology ID:
2022.emnlp-main.623
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9149–9156
Language:
URL:
https://aclanthology.org/2022.emnlp-main.623
DOI:
10.18653/v1/2022.emnlp-main.623
Bibkey:
Cite (ACL):
Alex Fabbri, Prafulla Kumar Choubey, Jesse Vig, Chien-Sheng Wu, and Caiming Xiong. 2022. Improving Factual Consistency in Summarization with Compression-Based Post-Editing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9149–9156, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Improving Factual Consistency in Summarization with Compression-Based Post-Editing (Fabbri et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.623.pdf