Rethinking the Agreement in Human Evaluation Tasks

Jacopo Amidei, Paul Piwek, Alistair Willis


Abstract
Human evaluations are broadly thought to be more valuable the higher the inter-annotator agreement. In this paper we examine this idea. We will describe our experiments and analysis within the area of Automatic Question Generation. Our experiments show how annotators diverge in language annotation tasks due to a range of ineliminable factors. For this reason, we believe that annotation schemes for natural language generation tasks that are aimed at evaluating language quality need to be treated with great care. In particular, an unchecked focus on reduction of disagreement among annotators runs the danger of creating generation goals that reward output that is more distant from, rather than closer to, natural human-like language. We conclude the paper by suggesting a new approach to the use of the agreement metrics in natural language generation evaluation tasks.
Anthology ID:
C18-1281
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3318–3329
Language:
URL:
https://aclanthology.org/C18-1281
DOI:
Bibkey:
Cite (ACL):
Jacopo Amidei, Paul Piwek, and Alistair Willis. 2018. Rethinking the Agreement in Human Evaluation Tasks. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3318–3329, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Rethinking the Agreement in Human Evaluation Tasks (Amidei et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/C18-1281.pdf
Data
SQuAD