Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation

Yixin Liu, Alexander Fabbri, Yilun Zhao, Pengfei Liu, Shafiq Joty, Chien-Sheng Wu, Caiming Xiong, Dragomir Radev


Abstract
Interpretability and efficiency are two important considerations for the adoption of neural automatic metrics. In this work, we develop strong-performing automatic metrics for reference-based summarization evaluation, based on a two-stage evaluation pipeline that first extracts basic information units from one text sequence and then checks the extracted units in another sequence. The metrics we developed include two-stage metrics that can provide high interpretability at both the fine-grained unit level and summary level, and one-stage metrics that achieve a balance between efficiency and interpretability. We make the developed tools publicly available at https://github.com/Yale-LILY/AutoACU.
Anthology ID:
2023.emnlp-main.1018
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16360–16368
Language:
URL:
https://aclanthology.org/2023.emnlp-main.1018
DOI:
10.18653/v1/2023.emnlp-main.1018
Bibkey:
Cite (ACL):
Yixin Liu, Alexander Fabbri, Yilun Zhao, Pengfei Liu, Shafiq Joty, Chien-Sheng Wu, Caiming Xiong, and Dragomir Radev. 2023. Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16360–16368, Singapore. Association for Computational Linguistics.
Cite (Informal):
Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation (Liu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.1018.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.1018.mp4