Evaluation of Really Good Grammatical Error Correction
Robert Östling, Katarina Gillholm, Murathan Kurfalı, Marie Mattson, Mats Wirén
Abstract
Traditional evaluation methods for Grammatical Error Correction (GEC) fail to fully capture the full range of system capabilities and objectives. The emergence of large language models (LLMs) has further highlighted the shortcomings of these evaluation strategies, emphasizing the need for a paradigm shift in evaluation methodology. In the current study, we perform a comprehensive evaluation of various GEC systems using a recently published dataset of Swedish learner texts. The evaluation is performed using established evaluation metrics as well as human judges. We find that GPT-3 in a few-shot setting by far outperforms previous grammatical error correction systems for Swedish, a language comprising only about 0.1% of its training data. We also found that current evaluation methods contain undesirable biases that a human evaluation is able to reveal. We suggest using human post-editing of GEC system outputs to analyze the amount of change required to reach native-level human performance on the task, and provide a dataset annotated with human post-edits and assessments of grammaticality, fluency and meaning preservation of GEC system outputs.- Anthology ID:
- 2024.lrec-main.584
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 6582–6593
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.584
- DOI:
- Cite (ACL):
- Robert Östling, Katarina Gillholm, Murathan Kurfalı, Marie Mattson, and Mats Wirén. 2024. Evaluation of Really Good Grammatical Error Correction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6582–6593, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Evaluation of Really Good Grammatical Error Correction (Östling et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.584.pdf