Abstract
Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statistical models for assessing factuality have been explored, there is no clear picture of what errors are most important to target or where current techniques are succeeding and failing. We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarization, and study factuality at the word-, dependency-, and sentence-level. Our observations are threefold. First, exhibited factual errors differ significantly across datasets, and commonly-used training sets of simple synthetic errors do not reflect errors made on abstractive datasets like XSum. Second, human-labeled data with fine-grained annotations provides a more effective training signal than sentence-level annotations or synthetic data. Finally, we show that our best factuality detection model enables training of more factual XSum summarization models by allowing us to identify non-factual tokens in the training data.- Anthology ID:
- 2021.naacl-main.114
- 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
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1449–1462
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.114
- DOI:
- 10.18653/v1/2021.naacl-main.114
- Cite (ACL):
- Tanya Goyal and Greg Durrett. 2021. Annotating and Modeling Fine-grained Factuality in Summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1449–1462, Online. Association for Computational Linguistics.
- Cite (Informal):
- Annotating and Modeling Fine-grained Factuality in Summarization (Goyal & Durrett, NAACL 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.114.pdf
- Code
- tagoyal/factuality-datasets + additional community code
- Data
- CNN/Daily Mail