| 講演名 | 2018-06-01 Readability Categorization of Japan EIKEN Document using Machine Learning with TF-IDF Rupasingha Arachchilage Hiruni Madhusha Rupasingha(会津大), Takeda Yui(会津大), Incheon Paik(会津大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | Understanding of the readability level and improvements of the text are needed for a specific audience. Accordingly, automatic measurement of text readability has been important issue and there have been many approaches to solve it. Classical readability is measured by readability formulas, and more recent research have employed machine learning algorithms. However, those machine learning approaches use complex features such as linguistic and grammatical features to hinder calculating correct readability score. In this paper, we investigate which features available as input to machine learning improves the performance more easily and accurately. We experiment the readability categorization by three kinds of feature vectors: readability score, Term Frequency-Inverse Document Frequency (TF-IDF), and the combination of them. The classification results by TF-IDF only give accurate results than other two features. |
| 抄録(英) | Understanding of the readability level and improvements of the text are needed for a specific audience. Accordingly, automatic measurement of text readability has been important issue and there have been many approaches to solve it. Classical readability is measured by readability formulas, and more recent research have employed machine learning algorithms. However, those machine learning approaches use complex features such as linguistic and grammatical features to hinder calculating correct readability score. In this paper, we investigate which features available as input to machine learning improves the performance more easily and accurately. We experiment the readability categorization by three kinds of feature vectors: readability score, Term Frequency-Inverse Document Frequency (TF-IDF), and the combination of them. The classification results by TF-IDF only give accurate results than other two features. |
| キーワード(和) | Readability / Eiken Document / Document Classification / Machine Learning |
| キーワード(英) | Readability / Eiken Document / Document Classification / Machine Learning |
| 資料番号 | SC2018-7 |
| 発行日 | 2018-05-25 (SC) |
| 研究会情報 | |
| 研究会 | SC |
|---|---|
| 開催期間 | 2018/6/1(から2日開催) |
| 開催地（和） | 会津大学 UBIC 3D Theater |
| 開催地（英） | UBIC 3D Theater, University of Aizu |
| テーマ（和） | 「第4次産業革命のためのサービスコンピューティング」および一般 |
| テーマ（英） | Service Computing for the 4th Industrial Revolution and Other Issues |
| 委員長氏名（和） | 中村 匡秀(神戸大) |
| 委員長氏名（英） | Masahide Nakamura(Kobe Univ.) |
| 副委員長氏名（和） | 菊地 伸治(会津大) / 山登 庸次(NTT) |
| 副委員長氏名（英） | Shinji Kikuchi(Univ. of Aizu) / Yoji Yamato(NTT) |
| 幹事氏名（和） | 細野 繁(NEC) / 木村 功作(富士通研) |
| 幹事氏名（英） | Shigeru Hosono(NEC) / Kosaku Kimura(Fujitsu Lab.) |
| 幹事補佐氏名（和） | |
| 幹事補佐氏名（英） | |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Service Computing |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Readability Categorization of Japan EIKEN Document using Machine Learning with TF-IDF |
| サブタイトル（和） | |
| キーワード(1)（和/英） | Readability / Readability |
| キーワード(2)（和/英） | Eiken Document / Eiken Document |
| キーワード(3)（和/英） | Document Classification / Document Classification |
| キーワード(4)（和/英） | Machine Learning / Machine Learning |
| 第 1 著者 氏名（和/英） | Rupasingha Arachchilage Hiruni Madhusha Rupasingha / Rupasingha Arachchilage Hiruni Madhusha Rupasingha |
| 第 1 著者 所属（和/英） | University of Aizu(略称：会津大) University of Aizu(略称：UoA) |
| 第 2 著者 氏名（和/英） | Takeda Yui / Takeda Yui |
| 第 2 著者 所属（和/英） | University of Aizu(略称：会津大) University of Aizu(略称：UoA) |
| 第 3 著者 氏名（和/英） | Incheon Paik / Incheon Paik |
| 第 3 著者 所属（和/英） | University of Aizu(略称：会津大) University of Aizu(略称：UoA) |
| 発表年月日 | 2018-06-01 |
| 資料番号 | SC2018-7 |
| 巻番号（vol） | vol.118 |
| 号番号（no） | SC-72 |
| ページ範囲 | pp.37-42(SC), |
| ページ数 | 6 |
| 発行日 | 2018-05-25 (SC) |