TY - GEN
T1 - Focal Training and Tagger Decouple for Grammatical Error Correction
AU - Tan, Minghuan
AU - Yang, Min
AU - Xu, Ruifeng
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - In this paper, we investigate how to improve tagging-based Grammatical Error Correction models. We address two issues of current tagging-based approaches, label imbalance issue, and tagging entanglement issue. Then we propose to down-weight the loss of correctly classified labels using Focal Loss and decouple the error detection layer from the label tagging layer through an extra self-attention-based matching module. Experiments on three recent Chinese Grammatical Error Correction datasets show that our proposed methods are effective. We further analyze choices of hyper-parameters for Focal Loss and inference tweaking.
AB - In this paper, we investigate how to improve tagging-based Grammatical Error Correction models. We address two issues of current tagging-based approaches, label imbalance issue, and tagging entanglement issue. Then we propose to down-weight the loss of correctly classified labels using Focal Loss and decouple the error detection layer from the label tagging layer through an extra self-attention-based matching module. Experiments on three recent Chinese Grammatical Error Correction datasets show that our proposed methods are effective. We further analyze choices of hyper-parameters for Focal Loss and inference tweaking.
UR - https://www.scopus.com/pages/publications/85175445214
U2 - 10.18653/v1/2023.findings-acl.370
DO - 10.18653/v1/2023.findings-acl.370
M3 - 会议稿件
AN - SCOPUS:85175445214
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 5978
EP - 5985
BT - Findings of the Association for Computational Linguistics, ACL 2023
PB - Association for Computational Linguistics (ACL)
T2 - Findings of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -