Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction
Published in ACL 2023, pages 7180–7188, 2023
Recommended citation: 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. https://aclanthology.org/2023.findings-acl.449/
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.
Recommended citation: 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.