How Much Annotation is Needed to Compare Summarization Models?

Chantal Shaib, Joe Barrow, Alexa Siu, Byron Wallace, Ani Nenkova

Abstract
Modern instruction-tuned models have become highly capable in text generation tasks such as summarization, and are expected to be released at a steady pace. In practice one may now wish to choose confidently, but with minimal effort, the best performing summarization model when applied to a new domain or purpose. In this work, we empirically investigate the test sample size necessary to select a preferred model in the context of news summarization. Empirical results reveal that comparative evaluation converges quickly for both automatic and human evaluation, with clear preferences for a system emerging from under 100 examples. The human preference data allows us to quantify how well automatic scores can reproduce preference rankings across a variety of downstream summarization tasks. We find that, while automatic metrics are stable at smaller sample sizes, only some automatic metrics are able to moderately predict model win rates according to human preference.
Anthology ID:
2024.hcinlp-1.5
Volume:
Proceedings of the Third Workshop on Bridging Human--Computer Interaction and Natural Language Processing
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Su Lin Blodgett, Amanda Cercas Curry, Sunipa Dey, Michael Madaio, Ani Nenkova, Diyi Yang, Ziang Xiao
Venues:
HCINLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–59
Language:
URL:
https://aclanthology.org/2024.hcinlp-1.5
DOI:
10.18653/v1/2024.hcinlp-1.5
Bibkey:
Cite (ACL):
Chantal Shaib, Joe Barrow, Alexa Siu, Byron Wallace, and Ani Nenkova. 2024. How Much Annotation is Needed to Compare Summarization Models?. In Proceedings of the Third Workshop on Bridging Human--Computer Interaction and Natural Language Processing, pages 51–59, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
How Much Annotation is Needed to Compare Summarization Models? (Shaib et al., HCINLP-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.hcinlp-1.5.pdf
PDF Search