Towards Automatic Error Type Classification of Japanese Language Learners' Writings
Hiromi Oyama, Mamoru Komachi, Yūji Matsumoto · 2013
Learner corpora are receiving special attention as an invaluable source of educational feedback and are expected to improve teaching materials and methodology. However, they include various types of incorrect sentences. Error type classification is an important task in learner corpora which enables clarifying for learners why a certain sentence is classified as incorrect in order to help learners not to repeat errors. To address this issue, we defined a set of error type criteria and conducted automatic classification of errors into error types in the sentences from the NAIST Goyo Corpus and achieved an accuracy of 77.6%. We also tried inter-corpus evaluation of our system on the Lang-8 corpus of learner Japanese and achieved an accuracy of 42.3%. To know the accuracy, we also investigated the classification method by human judgement and compared the difference in classification between the machine and the human.