0

DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely

Repurposing reference-based metrics to be reference-free improves their performance in summary quality assessment, with zero-shot BERTScore outperforming its original version and other reference-free metrics.

Year
2022
Venue
arXiv 2022
Authors
8
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2212.10013v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

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.

Authors

8