Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction

TL;DR

This paper introduces AMR-GEC, a novel seq-to-seq model that uses denoised Abstract Meaning Representation to improve grammatical error correction, reducing training time while maintaining competitive performance.

Contribution

It is the first to incorporate denoised AMR into GEC, enhancing model reliability and efficiency compared to existing approaches.

Findings

AMR-GEC performs comparably to strong baselines.

Reduces training time by 32% compared to T5.

Inference time remains similar to baseline models.

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.