Exploiting Unlabeled Data for Neural Grammatical Error Detection
This addresses the challenge of grammatical error detection for non-native writers, but it is incremental as it builds on existing neural methods with unlabeled data.
The paper tackled the problem of limited annotated data for grammatical error detection by proposing a method to utilize unlabeled data, resulting in a neural network model that significantly outperformed SVMs and convolutional networks.
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.