Identifying and correcting grammatical errors in the text written by non-native writers have received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven gram-matical 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 SVM and convolutional networks with fixed-size context window.