Abstract
“Grammatical error correction (GEC) aims at correcting texts with different types of grammatical errors into natural and correct forms. Due to the difference of error type distribution and error density, current grammatical error correction systems may over-correct writings and produce a low precision. To address this issue, in this paper, we propose a dynamic negative example construction method for grammatical error correction using contrastive learning. The proposed method can construct sufficient negative examples with diverse grammatical errors, and can be dynamically used during model training. The constructed negative examples are beneficial for the GEC model to correct sentences precisely and suppress the model from over-correction. Experimental results show that our proposed method enhances model precision, proving the effectiveness of our method.”- Anthology ID:
- 2022.ccl-1.83
- Volume:
- Proceedings of the 21st Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Nanchang, China
- Editors:
- Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 945–957
- Language:
- English
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.ccl-1.83/
- DOI:
- Cite (ACL):
- He Junyi, Zhuang Junbin, and Li Xia. 2022. Dynamic Negative Example Construction for Grammatical Error Correction using Contrastive Learning. In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 945–957, Nanchang, China. Chinese Information Processing Society of China.
- Cite (Informal):
- Dynamic Negative Example Construction for Grammatical Error Correction using Contrastive Learning (Junyi et al., CCL 2022)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.ccl-1.83.pdf