Adversarial Grammatical Error Correction

Vipul Raheja, Dimitris Alikaniotis


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.
Anthology ID:
2020.findings-emnlp.275
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3075–3087
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.275
DOI:
10.18653/v1/2020.findings-emnlp.275
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.275.pdf
Optional supplementary material:
 2020.findings-emnlp.275.OptionalSupplementaryMaterial.pdf
Data
FCE