223-238

• Kotani, Katsunori
• Yoshimi, Takehiko

The present paper introduces an automatic classification system for assisting second language (L2) writing evaluation. This system, which classifies sentences written by L2 learners as either native speaker-like or learner-like sentences, is constructed by machine learning algorithms using word-alignment distributions as classification features for detecting word-byword translated expressions. The experimental results demonstrated that our classification system provided adequate classification results with respect to (i) high classification accuracy, (ii) classification results reflecting the properties of L2 learner sentences, and (iii) identification of learner-like expressions. These results suggest that our classification system can be used to evaluate L2 learner sentences.

• Educational sciences

• Εκπαίδευση

This work was supported in part by Grant-in-Aid for Scientific Research (B) (22300299).