Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction

Hejing Cao, Dongyan Zhao


Abstract
Grammatical Error Correction (GEC) is the task of correcting errorful sentences into grammatically correct, semantically consistent, and coherent sentences. Popular GEC models either use large-scale synthetic corpora or use a large number of human-designed rules. The former is costly to train, while the latter requires quite a lot of human expertise. In recent years, AMR, a semantic representation framework, has been widely used by many natural language tasks due to its completeness and flexibility. A non-negligible concern is that AMRs of grammatically incorrect sentences may not be exactly reliable. In this paper, we propose the AMR-GEC, a seq-to-seq model that incorporates denoised AMR as additional knowledge. Specifically, We design a semantic aggregated GEC model and explore denoising methods to get AMRs more reliable. Experiments on the BEA-2019 shared task and the CoNLL-2014 shared task have shown that AMR-GEC performs comparably to a set of strong baselines with a large number of synthetic data. Compared with the T5 model with synthetic data, AMR-GEC can reduce the training time by 32% while inference time is comparable. To the best of our knowledge, we are the first to incorporate AMR for grammatical error correction.
Anthology ID:
2023.findings-acl.449
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:
7180–7188
Language:
URL:
https://aclanthology.org/2023.findings-acl.449
DOI:
10.18653/v1/2023.findings-acl.449
Bibkey:
Cite (ACL):
Hejing Cao and Dongyan Zhao. 2023. Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7180–7188, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction (Cao & Zhao, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.449.pdf