English

Adversarial Grammatical Error Correction

Computation and Language 2020-10-07 v1 Artificial Intelligence Machine Learning

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.

Keywords

Cite

@article{arxiv.2010.02407,
  title  = {Adversarial Grammatical Error Correction},
  author = {Vipul Raheja and Dimitrios Alikaniotis},
  journal= {arXiv preprint arXiv:2010.02407},
  year   = {2020}
}

Comments

13 Pages, EMNLP 2020

R2 v1 2026-06-23T19:04:09.207Z