Automatic Chinglish Identification Based on Semantic Distances Calculation

摘要

Writing has been considered as an effective way to measure a language learner's language proficiency. With labor and resources saved, writing test is entering into an era in need of Automated Essay Scoring (AES). However, its further promotion in China is limited by the negative transfer of non-native learners. Therefore, this study proposed a new way to identify Chinglish, which obstructs the development of AES in China. This WordNet-based method starts with dealing with semantic relations between English verbs, calculates semantic distances between subjects and objects and then realizes the identification of Chinglish by threshold. Experiments conducted in one university show that the proposed way performs well in identifying Chinglish in college students' English essays.