A Correcting Model for Preposition Error in English Essays of Chinese Student Based on Hybrid Features Classification
Ya Zhou, Zun He Rong, Gui Min Huang · Applied Mechanics and Materials · 2014
In this paper, we propose an automatic preposition correction method for Chinese learners of English. Our corpus comes from Chinese learners of English Corpus (CLEC). We use N-gram model to extract the semantic features based on the form of the word in context, part of speech tagging and syntactic parse tree. Meanwhile, this paper proposes a new method based on mutual information and improves the training and classification method. This method’s performance has been improved in terms of both effectiveness and efficiency, and the results show a significant improvement compared with the previous results.