Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVMs and convolutional networks with fixed-size context window.
@article{arxiv.1611.08987,
title = {Exploiting Unlabeled Data for Neural Grammatical Error Detection},
author = {Zhuoran Liu and Yang Liu},
journal= {arXiv preprint arXiv:1611.08987},
year = {2016}
}