Research on Developing Learning Materials for the Japanese Academic Writing Based on the Mined Data from XML Corpora

2015 Fiscal Year Final Research Report

• Project/Area Number: 25540163
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Learning support system
• Research Institution: Osaka University
• Principal Investigator: Hori Kazunari 大阪大学, 全学教育推進機構, 准教授 (80270346)
• Co-Investigator(Kenkyū-buntansha): Sakajiri Akihiro 大阪大学, 全学教育推進機構, 准教授 (30512933) ; Ishijima Dai 大阪府立産業技術総合研究所, 製品信頼性科, 主任研究員 (80359398)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: アカデミック・ライティング / データマイニング / 日本語コーパス / 大学リポジトリ / 学習コンテンツ / コロケーション / BCCWJ / eラーニング

Outline of Final Research Achievements

We have mined linguistic characteristics from academic corpora, in order to provide them as learning materials for our writing classes, and so far obtained the following three results.
(1)Obtained the frequency of verbs and nouns used in the high school textbook data from “The Balanced Corpus of Contemporary Written Japanese”(BCCWJ).(2)Developed and executed the procedure for mining both academic and technical sentences, using Comainu software which imparts the long-unit-word morphological information to plain text data.(3)Obtained the long-unit-word verb and noun frequency through mining information from academic sentences (approx. 6,000 characters) and technical sentences (approx. 15,000 characters).

Free Research Field

自然言語処理、数理工学