Mining sequential patterns and tree patterns to detect erroneous sentences

Abstract

An important application area of detecting erroneous sentences is to provide feedback for writers of English as a Second Language. This problem is difficult since both erroneous and correct sentences are diversified. In this paper, we propose a novel approach to identifying erroneous sentences. We first mine labeled tree patterns and sequential patterns to characterize both erroneous and correct sentences. Then the discovered patterns are utilized in two ways to distinguish correct sentences from erroneous sentences: (1) the patterns are transformed into sentence features for existing classification models, e.g., SVM; (2) the patterns are used to build a rulebased classification model. Experimental results show that both techniques are promising while the second technique outperforms the first approach. Moreover, the classification model in the second proposal is easy to understand, and we can provide intuitive explanation for classification results.