Adversarial Grammatical Error Correction

TL;DR

This paper introduces an adversarial learning framework for grammatical error correction using a generator-discriminator setup, achieving competitive results with traditional NMT-based methods.

Contribution

It presents a novel adversarial approach combining Transformer generators and discriminator models for GEC, with a unique training process involving policy gradients.

Findings

Achieves competitive GEC quality on standard datasets

Demonstrates effectiveness of adversarial training in GEC

Outperforms some baseline models in accuracy

Abstract

Recent works in Grammatical Error Correction (GEC) have leveraged the progress in Neural Machine Translation (NMT), to learn rewrites from parallel corpora of grammatically incorrect and corrected sentences, achieving state-of-the-art results. At the same time, Generative Adversarial Networks (GANs) have been successful in generating realistic texts across many different tasks by learning to directly minimize the difference between human-generated and synthetic text. In this work, we present an adversarial learning approach to GEC, using the generator-discriminator framework. The generator is a Transformer model, trained to produce grammatically correct sentences given grammatically incorrect ones. The discriminator is a sentence-pair classification model, trained to judge a given pair of grammatically incorrect-correct sentences on the quality of grammatical correction. We pre-train both the discriminator and the generator on parallel texts and then fine-tune them further using a policy gradient method that assigns high rewards to sentences which could be true corrections of the grammatically incorrect text. Experimental results on FCE, CoNLL-14, and BEA-19 datasets show that Adversarial-GEC can achieve competitive GEC quality compared to NMT-based baselines.