Automated Error Detection of Vocabulary Usage in College English Writing

Abstract

The frequencies of binary adjacent word pairs (BAWPs) in large corpus of native English speakers were counted to retrieve the data of BAWPs as the foundation of the research. BAWPs in Chinese college students’ English compositions were tagged with the frequencies appearing in native corpus. Researchers’ examination finds that about 46% of the BAWPs in students’ compositions with the tagged frequency lower than 10 are language errors and close to 37% with the tagged frequency lower than 30 are errors. Misreport patterns were summarized and more than 100 filter rules of misreport were constructed. Combining with these rules, the ratios of actual errors are raised to over 60% and 48% for these two threshold values respectively, which can greatly facilitate college English writing.