LET: Leveraging Error Type Information for Grammatical Error Correction

Lingyu Yang, Hongjia Li, Lei Li, Chengyin Xu, Shutao Xia, Chun Yuan

Abstract
Grammatical error correction (GEC) aims to correct errors in given sentences and is significant to many downstream natural language understanding tasks. Recent work introduces the idea of grammatical error detection (GED) to improve the GEC task performance. In contrast, these explicit multi-stage works propagate and amplify the problem of misclassification of the GED module. To introduce more convincing error type information, we propose an end-to-end framework in this paper, which Leverages Error Type (LET) information in the generation process. First, the input text is fed into a classification module to obtain the error type corresponding to each token. Then, we introduce the category information into the decoder’s input and cross-attention module in two ways, respectively. Experiments on various datasets show that our proposed method outperforms existing methods by a clear margin.
Anthology ID:
2023.findings-acl.371
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5986–5998
Language:
URL:
https://aclanthology.org/2023.findings-acl.371
DOI:
10.18653/v1/2023.findings-acl.371
Bibkey:
Cite (ACL):
Lingyu Yang, Hongjia Li, Lei Li, Chengyin Xu, Shutao Xia, and Chun Yuan. 2023. LET: Leveraging Error Type Information for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5986–5998, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
LET: Leveraging Error Type Information for Grammatical Error Correction (Yang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.371.pdf
PDF Search