Chinese Grammatical Correction Using BERT-based Pre-trained Model
Hongfei Wang, Michiki Kurosawa, Satoru Katsumata, Mamoru Komachi
Abstract
In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we verify the effectiveness of two methods that incorporate a pre-trained model into an encoder-decoder model on Chinese grammatical error correction tasks. We also analyze the error type and conclude that sentence-level errors are yet to be addressed.- Anthology ID:
- 2020.aacl-main.20
- Volume:
- Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Editors:
- Kam-Fai Wong, Kevin Knight, Hua Wu
- Venue:
- AACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 163–168
- Language:
- URL:
- https://aclanthology.org/2020.aacl-main.20
- DOI:
- Cite (ACL):
- Hongfei Wang, Michiki Kurosawa, Satoru Katsumata, and Mamoru Komachi. 2020. Chinese Grammatical Correction Using BERT-based Pre-trained Model. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 163–168, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- Chinese Grammatical Correction Using BERT-based Pre-trained Model (Wang et al., AACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.aacl-main.20.pdf