SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction
Ryoma Yoshimura, Masahiro Kaneko, Tomoyuki Kajiwara, Mamoru Komachi
Abstract
We propose a reference-less metric trained on manual evaluations of system outputs for grammatical error correction (GEC). Previous studies have shown that reference-less metrics are promising; however, existing metrics are not optimized for manual evaluations of the system outputs because no dataset of the system output exists with manual evaluation. This study manually evaluates outputs of GEC systems to optimize the metrics. Experimental results show that the proposed metric improves correlation with the manual evaluation in both system- and sentence-level meta-evaluation. Our dataset and metric will be made publicly available.- Anthology ID:
- 2020.coling-main.573
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 6516–6522
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.573
- DOI:
- 10.18653/v1/2020.coling-main.573
- Cite (ACL):
- Ryoma Yoshimura, Masahiro Kaneko, Tomoyuki Kajiwara, and Mamoru Komachi. 2020. SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6516–6522, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction (Yoshimura et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.573.pdf
- Code
- kokeman/some
- Data
- GUG, JFLEG