CSynGEC: Incorporating Constituent-based Syntax for Grammatical Error Correction with a Tailored GEC-Oriented Parser

TL;DR

CSynGEC introduces a novel constituent-based syntax approach for grammatical error correction, leveraging a tailored parser and combining syntax formalism types to enhance correction performance.

Contribution

This work extends constituent-based syntax schemes for GEC, develops a GEC-oriented constituency parser, and explores combining syntax formalism types for improved correction accuracy.

Findings

Significant improvements over strong baselines in GEC tasks.

Intra-model syntax combination enhances recall.

Inter-model syntax combination improves precision.

Abstract

Recently, Zhang et al. (2022) propose a syntax-aware grammatical error correction (GEC) approach, named SynGEC, showing that incorporating tailored dependency-based syntax of the input sentence is quite beneficial to GEC. This work considers another mainstream syntax formalism, i.e., constituent-based syntax. By drawing on the successful experience of SynGEC, we first propose an extended constituent-based syntax scheme to accommodate errors in ungrammatical sentences. Then, we automatically obtain constituency trees of ungrammatical sentences to train a GEC-oriented constituency parser by using parallel GEC data as a pivot. For syntax encoding, we employ the graph convolutional network (GCN). Experimental results show that our method, named CSynGEC, yields substantial improvements over strong baselines. Moreover, we investigate the integration of constituent-based and dependency-based syntax for GEC in two ways: 1) intra-model combination, which means using separate GCNs to encode both kinds of syntax for decoding in a single model; 2)inter-model combination, which means gathering and selecting edits predicted by different models to achieve final corrections. We find that the former method improves recall over using one standalone syntax formalism while the latter improves precision, and both lead to better F0.5 values.