A Multi-model SVR Approach to Estimating the CEFR Proficiency Level of Grammar Item Features

Brendan Flanagan, Sachio Hirokawa, Emiko Kaneko, Emi Izumi, Hiroaki Ogata

    研究成果: 書籍/レポート タイプへの寄稿会議への寄与

    抄録

    Analysis of publicly available language learning corpora can be useful for extracting characteristic features of learners from different proficiency levels. This can then be used to support language learning research and the creation of educational resources. In this paper, we classify the words and parts of speech of transcripts from different speaking proficiency levels found in the NICT-JLE corpus. The characteristic features of learners who have the equivalent spoken proficiency of CEFR levels A1 through to B2 were extracted by analyzing the data with the support vector machine method. In particular, we apply feature selection to find a set of characteristic features that achieve optimal classification performance, which can be used to predict spoken learner proficiency.

    本文言語英語
    ホスト出版物のタイトルProceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017
    編集者Kiyota Hashimoto, Naoki Fukuta, Tokuro Matsuo, Sachio Hirokawa, Masao Mori, Masao Mori
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ521-526
    ページ数6
    ISBN(電子版)9781538606216
    DOI
    出版ステータス出版済み - 11月 15 2017
    イベント6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017 - Hamamatsu, Shizuoka, 日本
    継続期間: 7月 9 2017 → …

    出版物シリーズ

    名前Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017

    その他

    その他6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017
    国/地域日本
    CityHamamatsu, Shizuoka
    Period7/9/17 → …

    !!!All Science Journal Classification (ASJC) codes

    • 人工知能
    • コンピュータ ネットワークおよび通信
    • コンピュータ サイエンスの応用
    • 情報システム
    • 情報システムおよび情報管理

    フィンガープリント

    「A Multi-model SVR Approach to Estimating the CEFR Proficiency Level of Grammar Item Features」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル