Automatically Detecting Syntactic Errors in Sentences Writing by Learners of Chinese as a Foreign Language

Computational Linguistics and Chinese Language Processing Vol. 20, No. 1, June 2015, pp. 49-64 49  The Association for Computational Linguistics and Chinese Language Processing Automatically Detecting Syntactic Errors in Sentences Written by Learners of Chinese as a Foreign Language Tao-Hsing CHANG, Yao-Ting SUNG and Jia-Fei HONG Abstract This paper proposed a method that can automatically detect syntax errors in Chinese sentences. The algorithm for identifying syntax errors proposed in this study is known as KNGED, which uses a large database of rules to identify whether syntax errors exist in a sentence. The rules were generated either manually or automatically. This paper further proposed an algorithm for identifying the type of error that a sentence contained. Experimental results shown that the false positive rate and F1-measure of the proposed method for detecting syntax errors in Chinese sentences are 0.90 and 0.65. Keywords: Syntactic Errors, Chinese Grammar, Chinese Written Corpus. 1. Introduction The teaching of languages has always been an important area of research and a commercially viable market. An important topic of research is the means by which the linguistic abilities of learners can be enhanced efficiently. This is especially so for learners of foreign languages, who have to learn the target language within a limited time period while being in a non-immersive learning environment, unlike the ample time they had for learning their native language. Contrastive linguistics is a tool that can be used to improve the efficiency of learning a foreign language effectively. Since most learners would already have well-developed capabilities in their native language, pointing out and analyzing the differences between the native and foreign language can help learners to understand the differences between the two, thereby facilitating the conversion from the former to the latter.  Department of Computer Science and Information Engineering, National Kaohsiung University of Applied Sciences, Taiwan E-mail: changth@gm.kuas.edu.tw  Department of Educational Psychology and Counseling, National Taiwan Normal University, Taiwan E-mail: sungtc@ntnu.edu.tw  Department of Applied Chinese Language and Culture, National Taiwan Normal University, Taiwan E-mail: jiafeihong@ntnu.edu.tw 50 Tao-Hsing Chang et al. However, simply understanding the differences between two languages does not mean that a person can make the conversion from one to the other effectively in real-life usage situations. In comparative linguistics, two phenomena often appear in the patterns of language usage. First, since the types and quantity of differences are substantial, learners may not necessarily notice each and every difference between the native and foreign languages when using the latter. Second, when learners are not familiar with the linguistic differences, they become susceptible to the phenomenon of language transfer. An example is the use of suffixes that signal tenses of English verbs, which has no parallel in the grammar of Chinese verbs. Although learners of English are aware that they need to pay attention to the tenses of verbs, they often make the mistake of using the wrong tense. Learners must keep practicing to become familiar with the relevant linguistic differences. During the learning process, teachers must also point out …

Content truncated to 500 words