A Survey of Evaluation Metrics Used for NLG Systems
ACM Computing Surveys · 28.02.2023 · 55 (2) · 1-39
DOI: 10.1145/3485766 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 18.01.2022. Verfasst von Ananya B. Sai und 2 weiteren Autor:innen. Die Arbeit wurde bisher 174-mal zitiert (Crossref) und nennt 147 Literaturangaben. Gefördert von: Department of Computer Science and Engineering, Robert Bosch Center for Data Science and Artificial Intelligence.
Abstract (Originalsprache)
In the last few years, a large number of automatic evaluation metrics have been proposed for evaluating Natural Language Generation (NLG) systems. The rapid development and adoption of such automatic evaluation metrics in a relatively short time has created the need for a survey of these metrics. In this survey, we (i) highlight the challenges in automatically evaluating NLG systems, (ii) propose a coherent taxonomy for organising existing evaluation metrics, (iii) briefly describe different existing metrics, and finally (iv) discuss studies criticising the use of automatic evaluation metrics. We then conclude the article highlighting promising future directions of research.
Förderung
- Department of Computer Science and Engineering
- Robert Bosch Center for Data Science and Artificial Intelligence
Zitieren
APA
Sai, A. B., Mohankumar, A. K., & Khapra, M. M. (2023). A Survey of Evaluation Metrics Used for NLG Systems. ACM Computing Surveys, 55(2), 1-39. https://doi.org/10.1145/3485766
Vancouver
Sai AB, Mohankumar AK, Khapra MM. A Survey of Evaluation Metrics Used for NLG Systems. ACM Computing Surveys. 2023;55(2):1-39. doi:10.1145/3485766
BibTeX
@article{Sai2023,
author = {Sai, Ananya B. and Mohankumar, Akash Kumar and Khapra, Mitesh M.},
title = {A Survey of Evaluation Metrics Used for NLG Systems},
journal = {ACM Computing Surveys},
year = {2023},
volume = {55},
number = {2},
pages = {1--39},
doi = {10.1145/3485766}
}
EUVIMED