Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency

Wen Xiao, Giuseppe Carenini


Abstract
Discourse-aware techniques, including entity-aware approaches, play a crucial role in summarization. In this paper, we propose an entity-based SpanCopy mechanism to tackle the entity-level factual inconsistency problem in abstractive summarization, i.e. reducing the mismatched entities between the generated summaries and the source documents. Complemented by a Global Relevance component to identify summary-worthy entities, our approach demonstrates improved factual consistency while preserving saliency on four summarization datasets, contributing to the effective application of discourse-aware methods summarization tasks.
Anthology ID:
2023.codi-1.9
Volume:
Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Michael Strube, Chloe Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaiciga, Amir Zeldes
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
70–81
Language:
URL:
https://aclanthology.org/2023.codi-1.9
DOI:
10.18653/v1/2023.codi-1.9
Bibkey:
Cite (ACL):
Wen Xiao and Giuseppe Carenini. 2023. Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 70–81, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency (Xiao & Carenini, CODI 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.codi-1.9.pdf