Updated Headline Generation: Creating Updated Summaries for Evolving News Stories

Sheena Panthaplackel, Adrian Benton, Mark Dredze


Abstract
We propose the task of updated headline generation, in which a system generates a headline for an updated article, considering both the previous article and headline. The system must identify the novel information in the article update, and modify the existing headline accordingly. We create data for this task using the NewsEdits corpus by automatically identifying contiguous article versions that are likely to require a substantive headline update. We find that models conditioned on the prior headline and body revisions produce headlines judged by humans to be as factual as gold headlines while making fewer unnecessary edits compared to a standard headline generation model. Our experiments establish benchmarks for this new contextual summarization task.
Anthology ID:
2022.acl-long.446
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6438–6461
Language:
URL:
https://aclanthology.org/2022.acl-long.446
DOI:
10.18653/v1/2022.acl-long.446
Bibkey:
Cite (ACL):
Sheena Panthaplackel, Adrian Benton, and Mark Dredze. 2022. Updated Headline Generation: Creating Updated Summaries for Evolving News Stories. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6438–6461, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Updated Headline Generation: Creating Updated Summaries for Evolving News Stories (Panthaplackel et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.446.pdf