Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
Abstract
Modern summarization models generate highly fluent but often factually unreliable outputs. This motivated a surge of metrics attempting to measure the factuality of automatically generated summaries. Due to the lack of common benchmarks, these metrics cannot be compared. Moreover, all these methods treat factuality as a binary concept and fail to provide deeper insights on the kinds of inconsistencies made by different systems. To address these limitations, we devise a typology of factual errors and use it to collect human annotations of generated summaries from state-of-the-art summarization systems for the CNN/DM and XSum datasets. Through these annotations we identify the proportion of different categories of factual errors and benchmark factuality metrics, showing their correlation with human judgement as well as their specific strengths and weaknesses.- Anthology ID:
- 2021.naacl-main.383
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4812–4829
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.383
- DOI:
- 10.18653/v1/2021.naacl-main.383
- Cite (ACL):
- Artidoro Pagnoni, Vidhisha Balachandran, and Yulia Tsvetkov. 2021. Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4812–4829, Online. Association for Computational Linguistics.
- Cite (Informal):
- Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics (Pagnoni et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.naacl-main.383.pdf
- Code
- artidoro/frank