A Syntax-Guided Grammatical Error Correction Model with Dependency Tree Correction

TL;DR

This paper introduces a syntax-guided grammatical error correction model that leverages dependency trees and graph attention mechanisms to improve correction accuracy without relying on large pre-trained models.

Contribution

The work proposes a novel syntax-guided GEC model using dependency tree correction and data augmentation, enhancing grammatical error correction performance.

Findings

Achieves competitive results on public GEC benchmarks.

Utilizes dependency tree correction to improve syntactic knowledge accuracy.

Operates effectively without large pre-trained models.

Abstract

Grammatical Error Correction (GEC) is a task of detecting and correcting grammatical errors in sentences. Recently, neural machine translation systems have become popular approaches for this task. However, these methods lack the use of syntactic knowledge which plays an important role in the correction of grammatical errors. In this work, we propose a syntax-guided GEC model (SG-GEC) which adopts the graph attention mechanism to utilize the syntactic knowledge of dependency trees. Considering the dependency trees of the grammatically incorrect source sentences might provide incorrect syntactic knowledge, we propose a dependency tree correction task to deal with it. Combining with data augmentation method, our model achieves strong performances without using any large pre-trained models. We evaluate our model on public benchmarks of GEC task and it achieves competitive results.