Evaluating Two Web-based Grammar Checkers - Microsoft ESL Assistant and NTNU Statistical

Many ESL students need to improve writing skills to pass various language tests; thus, writing teachers need to read many compositions and provide feedback. To help ESL teachers reduce their teaching load and to give students faster feedback, various English grammar checkers have been developed. Few of these PC-based grammar checkers, however, are widely available to ESL learners. As the Internet has become an important tool for language education, web-based grammar checkers have begun to emerge. In this paper, we first introduce two new web-based grammar checkers (Microsoft ESL Assistant and NTNU statistical grammar checker) and then compare their performance. Ten common EFL errors selected from a large Chinese EFL learner corpus were used to test these two grammar checkers. The test results showed that the NTNU statistical checker was far more sensitive to various learner errors, and it could detect eight types of selected errors. Microsoft ESL Assistant could only deal with five types of errors. Moreover, these two checkers both could not deal with fragments and run-on sentences errors. It seems clear that both checkers have room for improvement before they can provide satisfactory service to ESL learners. The Microsoft ESL Assistant should expand its coverage to detect more learner errors. NTNU checker should reduce false alarms and indicate the locations of errors more accurately. Learner errors are indeed complicated for developers of grammar checkers, but the strong need for a functional grammar checker deserves CALL researchers’ special attention.