DocAsRef: An Empirical Study on Repurposing Reference-based Summary Quality Metrics as Reference-free Metrics
Forrest Bao, Ruixuan Tu, Ge Luo, Yinfei Yang, Hebi Li, Minghui Qiu, Youbiao He, Cen Chen
Abstract
Automated summary quality assessment falls into two categories: reference-based and reference-free. Reference-based metrics, historically deemed more accurate due to the additional information provided by human-written references, are limited by their reliance on human input. In this paper, we hypothesize that the comparison methodologies used by some reference-based metrics to evaluate a system summary against its corresponding reference can be effectively adapted to assess it against its source document, thereby transforming these metrics into reference-free ones. Experimental results support this hypothesis. After being repurposed reference-freely, the zero-shot BERTScore using the pretrained DeBERTa-large-MNLI model of <0.5B parameters consistently outperforms its original reference-based version across various aspects on the SummEval and Newsroom datasets. It also excels in comparison to most existing reference-free metrics and closely competes with zero-shot summary evaluators based on GPT-3.5.- Anthology ID:
- 2023.findings-emnlp.87
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1226–1235
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.87
- DOI:
- 10.18653/v1/2023.findings-emnlp.87
- Cite (ACL):
- Forrest Bao, Ruixuan Tu, Ge Luo, Yinfei Yang, Hebi Li, Minghui Qiu, Youbiao He, and Cen Chen. 2023. DocAsRef: An Empirical Study on Repurposing Reference-based Summary Quality Metrics as Reference-free Metrics. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1226–1235, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- DocAsRef: An Empirical Study on Repurposing Reference-based Summary Quality Metrics as Reference-free Metrics (Bao et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.87.pdf