Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction

TL;DR

This paper introduces VERNet, a neural model that leverages multiple hypotheses and reasoning mechanisms to improve grammatical error correction quality estimation and reranking, achieving state-of-the-art results.

Contribution

The paper proposes VERNet, a novel neural network that uses multiple hypotheses and reasoning graphs for enhanced GEC quality estimation and reranking.

Findings

VERNet achieves state-of-the-art grammatical error detection.

VERNet significantly improves GEC performance through hypothesis reranking.

The model outperforms existing quality estimation methods.

Abstract

Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.