Intrinsic Evaluation of Summarization Datasets

Rishi Bommasani, Claire Cardie


Abstract
High quality data forms the bedrock for building meaningful statistical models in NLP. Consequently, data quality must be evaluated either during dataset construction or *post hoc*. Almost all popular summarization datasets are drawn from natural sources and do not come with inherent quality assurance guarantees. In spite of this, data quality has gone largely unquestioned for many of these recent datasets. We perform the first large-scale evaluation of summarization datasets by introducing 5 intrinsic metrics and applying them to 10 popular datasets. We find that data usage in recent summarization research is sometimes inconsistent with the underlying properties of the data. Further, we discover that our metrics can serve the additional purpose of being inexpensive heuristics for detecting generically low quality examples.
Anthology ID:
2020.emnlp-main.649
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8075–8096
Language:
URL:
https://aclanthology.org/2020.emnlp-main.649
DOI:
10.18653/v1/2020.emnlp-main.649
Bibkey:
Cite (ACL):
Rishi Bommasani and Claire Cardie. 2020. Intrinsic Evaluation of Summarization Datasets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8075–8096, Online. Association for Computational Linguistics.
Cite (Informal):
Intrinsic Evaluation of Summarization Datasets (Bommasani & Cardie, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.649.pdf
Video:
 https://slideslive.com/38938755