Fact-based Content Weighting for Evaluating Abstractive Summarisation
Xinnuo Xu, Ondřej Dušek, Jingyi Li, Verena Rieser, Ioannis Konstas
Abstract
Abstractive summarisation is notoriously hard to evaluate since standard word-overlap-based metrics are insufficient. We introduce a new evaluation metric which is based on fact-level content weighting, i.e. relating the facts of the document to the facts of the summary. We fol- low the assumption that a good summary will reflect all relevant facts, i.e. the ones present in the ground truth (human-generated refer- ence summary). We confirm this hypothe- sis by showing that our weightings are highly correlated to human perception and compare favourably to the recent manual highlight- based metric of Hardy et al. (2019).- Anthology ID:
- 2020.acl-main.455
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5071–5081
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.455
- DOI:
- 10.18653/v1/2020.acl-main.455
- Cite (ACL):
- Xinnuo Xu, Ondřej Dušek, Jingyi Li, Verena Rieser, and Ioannis Konstas. 2020. Fact-based Content Weighting for Evaluating Abstractive Summarisation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5071–5081, Online. Association for Computational Linguistics.
- Cite (Informal):
- Fact-based Content Weighting for Evaluating Abstractive Summarisation (Xu et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.455.pdf