Detection-Correction Structure via General Language Model for Grammatical Error Correction

TL;DR

This paper proposes DeCoGLM, an integrated detection-correction framework using General Language Models for grammatical error correction, combining detection and correction in a single model to improve performance.

Contribution

It introduces a novel detection-correction structure within LLMs, enabling joint learning and improving GEC effectiveness over previous correction-only models.

Findings

Competitive performance on English and Chinese GEC datasets

Effective multi-task learning within a single model

Demonstrates the potential of detection-correction paradigm in LLMs

Abstract

Grammatical error correction (GEC) is a task dedicated to rectifying texts with minimal edits, which can be decoupled into two components: detection and correction. However, previous works have predominantly focused on direct correction, with no prior efforts to integrate both into a single model. Moreover, the exploration of the detection-correction paradigm by large language models (LLMs) remains underdeveloped. This paper introduces an integrated detection-correction structure, named DeCoGLM, based on the General Language Model (GLM). The detection phase employs a fault-tolerant detection template, while the correction phase leverages autoregressive mask infilling for localized error correction. Through the strategic organization of input tokens and modification of attention masks, we facilitate multi-task learning within a single model. Our model demonstrates competitive performance against the state-of-the-art models on English and Chinese GEC datasets. Further experiments present the effectiveness of the detection-correction structure in LLMs, suggesting a promising direction for GEC.