A System Providing Appropriate Alternative Candidates for Japanese Writing Using Word Co-occurrence

概要

論文の詳細を見る
Some of the unnatural co-occurrence expressions consisting of a noun n, a case particle c, and a verb v (<n, c, v>) used by learners of the Japanese language are caused by errors of verb selection. This paper proposes a method of providing candidates for appropriate alternative verbs to replace the v in learners' co-occurrence input <n, c, v>. We assume that a verb of unnatural co-occurrence (an error verb) tends to have an occurring environment similar to an appropriate verb (a possible correction of the error verb). Based on this hypothesis, the method produces candidates for appropriate alternative verbs that are estimated to comprise natural co-occurrences with the <n, c> portion of learners' co-occurrence input using statistical information from a large-scale Japanese corpus in descending order of occurring environment similarity with the original verb. Results of international students editing their own Japanese compositions using a system incorporating the proposed method showed that unnatural co-occurrence expressions in their compositions were reduced by 30%. This result shows that the proposed system is useful in aiding Japanese language learners' word selection in co-occurrence expressions.