Type-Driven Multi-Turn Corrections for Grammatical Error Correction

Shaopeng Lai, Qingyu Zhou, Jiali Zeng, Zhongli Li, Chao Li, Yunbo Cao, Jinsong Su


Abstract
Grammatical Error Correction (GEC) aims to automatically detect and correct grammatical errors. In this aspect, dominant models are trained by one-iteration learning while performing multiple iterations of corrections during inference. Previous studies mainly focus on the data augmentation approach to combat the exposure bias, which suffers from two drawbacks. First, they simply mix additionally-constructed training instances and original ones to train models, which fails to help models be explicitly aware of the procedure of gradual corrections. Second, they ignore the interdependence between different types of corrections. In this paper, we propose a Type-Driven Multi-Turn Corrections approach for GEC. Using this approach, from each training instance, we additionally construct multiple training instances, each of which involves the correction of a specific type of errors. Then, we use these additionally-constructed training instances and the original one to train the model in turn. Experimental results and in-depth analysis show that our approach significantly benefits the model training. Particularly, our enhanced model achieves state-of-the-art single-model performance on English GEC benchmarks. We release our code at Github.
Anthology ID:
2022.findings-acl.254
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3225–3236
Language:
URL:
https://aclanthology.org/2022.findings-acl.254
DOI:
10.18653/v1/2022.findings-acl.254
Bibkey:
Cite (ACL):
Shaopeng Lai, Qingyu Zhou, Jiali Zeng, Zhongli Li, Chao Li, Yunbo Cao, and Jinsong Su. 2022. Type-Driven Multi-Turn Corrections for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3225–3236, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Type-Driven Multi-Turn Corrections for Grammatical Error Correction (Lai et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.254.pdf
Software:
 2022.findings-acl.254.software.zip
Code
 deeplearnxmu/tmtc
Data
FCEWI-LOCNESS