Development of a Web-based Composition Support System --- Using Graph Clustering Methodologies Applied to an Associative Concepts Dictionary

In this study, we propose a new Web-based language learning system, called associative composition support system (ACSS). Whereas most existing composition systems intend a grammatical, syntactical support, the new system focuses on helping learners write more fluently. This semantic support is contrived on the assumption that different types of lexical association could encourage the vocabulary building and learning in a newly interesting way. ACSS provides associative information on/between words, based on a semantic network built by graph clustering methodologies (MCL by Van Dongen and RMCL by Jung) that are applied to an associative concepts dictionary