学習データが少量しかない場合の文書分類に関する一考察

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2011/08/01

タイトル(英語): A Note on Document Classification with Small Training Data

著者名: 前田　康成（北見工業大学情報システム工学科），吉田　秀樹（北見工業大学情報システム工学科），鈴木　正清（北見工業大学情報システム工学科），松嶋　敏泰（早稲田大学応用数理学科）

著者名(英語): Yasunari Maeda (Dept. of Computer Science, Kitami Institute of Technology), Hideki Yoshida (Dept. of Computer Science, Kitami Institute of Technology), Masakiyo Suzuki (Dept. of Computer Science, Kitami Institute of Technology), Toshiyasu Matsushima (Department of Applied Mathematics, Waseda University)

キーワード: 文書分類，学習データ，事前分布，事後分布　　document classification，training data，prior distribution，posterior distribution

要約(英語): Document classification is one of important topics in the field of NLP (Natural Language Processing). In the previous research a document classification method has been proposed which minimizes an error rate with reference to a Bayes criterion. But when the number of documents in training data is small, the accuracy of the previous method is low. So in this research we use estimating data in order to estimate prior distributions. When the training data is small the accuracy using estimating data is higher than the accuracy of the previous method. But when the training data is big the accuracy using estimating data is lower than the accuracy of the previous method. So in this research we also propose another technique whose accuracy is higher than the accuracy of the previous method when the training data is small, and is almost the same as the accuracy of the previous method when the training data is big.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.131 No.8 （2011）

本誌掲載ページ: 1459-1466 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/131/8/131_8_1459/_article/-char/ja/