A Simple but Effective Classification Model for Grammatical Error Correction

TL;DR

This paper introduces a neural network-based classification model for grammatical error correction that leverages context-aware features and outperforms existing methods on a standard benchmark.

Contribution

The study presents a novel neural network model using RNNs with attention for GEC, trained on large unlabeled corpora, and demonstrates superior performance.

Findings

Outperforms other classifiers on CoNLL-2014 with F0.5 45.05%

Uses end-to-end learned feature embeddings with RNNs and attention

Suitable for industrial deployment due to simplicity and effectiveness

Abstract

We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We propose a novel neural network based feature representation and classification model, trained using large text corpora without human annotations. Specifically we use RNNs with attention to represent both the left and right context of a target word. All feature embeddings are learned jointly in an end-to-end fashion. Experimental results show that our novel approach outperforms other classifier methods on the CoNLL-2014 test set (F0.5 45.05%). Our model is simple but effective, and is suitable for industrial production.