Finding a Balanced Degree of Automation for Summary Evaluation

Shiyue Zhang, Mohit Bansal


Abstract
Human evaluation for summarization tasks is reliable but brings in issues of reproducibility and high costs. Automatic metrics are cheap and reproducible but sometimes poorly correlated with human judgment. In this work, we propose flexible semiautomatic to automatic summary evaluation metrics, following the Pyramid human evaluation method. Semi-automatic Lite2Pyramid retains the reusable human-labeled Summary Content Units (SCUs) for reference(s) but replaces the manual work of judging SCUs’ presence in system summaries with a natural language inference (NLI) model. Fully automatic Lite3Pyramid further substitutes SCUs with automatically extracted Semantic Triplet Units (STUs) via a semantic role labeling (SRL) model. Finally, we propose in-between metrics, Lite2.xPyramid, where we use a simple regressor to predict how well the STUs can simulate SCUs and retain SCUs that are more difficult to simulate, which provides a smooth transition and balance between automation and manual evaluation. Comparing to 15 existing metrics, we evaluate human-metric correlations on 3 existing meta-evaluation datasets and our newly collected PyrXSum (with 100/10 XSum examples/systems). It shows that Lite2Pyramid consistently has the best summary-level correlations; Lite3Pyramid works better than or comparable to other automatic metrics; Lite2.xPyramid trades off small correlation drops for larger manual effort reduction, which can reduce costs for future data collection.
Anthology ID:
2021.emnlp-main.531
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6617–6632
Language:
URL:
https://aclanthology.org/2021.emnlp-main.531
DOI:
10.18653/v1/2021.emnlp-main.531
Bibkey:
Cite (ACL):
Shiyue Zhang and Mohit Bansal. 2021. Finding a Balanced Degree of Automation for Summary Evaluation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6617–6632, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Finding a Balanced Degree of Automation for Summary Evaluation (Zhang & Bansal, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.531.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.531.mp4
Code
 zhangshiyue/lite2-3pyramid