Automatic Metrics in Natural Language Generation: A survey of Current Evaluation Practices

Patricia Schmidtova, Saad Mahamood, Simone Balloccu, Ondrej Dusek, Albert Gatt, Dimitra Gkatzia, David M. Howcroft, Ondrej Platek, Adarsa Sivaprasad


Abstract
Automatic metrics are extensively used to evaluate Natural Language Processing systems. However, there has been increasing focus on how the are used and reported by practitioners within the field. In this paper, we have conducted a survey on the use of automatic metrics, focusing particularly on natural language generation tasks. We inspect which metrics are used as well as why they are chosen and how their use is reported. Our findings from this survey reveal significant shortcomings, including inappropriate metric usage, lack of implementation details and missing correlations with human judgements. We conclude with recommendations that we believe authors should follow to enable more rigour within the field.
Anthology ID:
2024.inlg-main.44
Volume:
Proceedings of the 17th International Natural Language Generation Conference
Month:
September
Year:
2024
Address:
Tokyo, Japan
Editors:
Saad Mahamood, Nguyen Le Minh, Daphne Ippolito
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
557–583
Language:
URL:
https://aclanthology.org/2024.inlg-main.44
DOI:
Bibkey:
Cite (ACL):
Patricia Schmidtova, Saad Mahamood, Simone Balloccu, Ondrej Dusek, Albert Gatt, Dimitra Gkatzia, David M. Howcroft, Ondrej Platek, and Adarsa Sivaprasad. 2024. Automatic Metrics in Natural Language Generation: A survey of Current Evaluation Practices. In Proceedings of the 17th International Natural Language Generation Conference, pages 557–583, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Automatic Metrics in Natural Language Generation: A survey of Current Evaluation Practices (Schmidtova et al., INLG 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.inlg-main.44.pdf