|
JAIST Repository >
a. 知識科学研究科・知識科学系 >
a10. 学術雑誌論文等 >
a10-1. 雑誌掲載論文 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/9211
|
| タイトル: | Augmented Mutual Information for Multi-word Extraction |
| 著者: | Zhang, Wen
Yoshida, Taketoshi
Ho, Tu Bao
Tang, Xijin |
| キーワード: | Multi-word extraction
Mutual information
Augmented mutual information
Word dependency |
| 発行日: | 2009-02 |
| 出版者: | ICIC International |
| 誌名: | International Journal of Innovative Computing, Information and Control |
| 巻: | 5 |
| 号: | 2 |
| 開始ページ: | 543 |
| 終了ページ: | 554 |
| 抄録: | In order to extract multi-words from documents, mutual information (MI), as a statistical method, is the most popular solution under consideration. However, there are two kinds of deficiencies inherent in MI. One is the problem of unilateral cooccurrence, and the other is rare occurrence problem. To attack these two problems, augmented mutual information (AMI) is proposed in this paper to measure word dependency for multi-word extraction. We prove theoretically that AMI has the capacity to approximate MI to capture the independency of individual words, but it will amplify the significance of dependent individual words which may be possible multi-words. And ourexperimental results on Chinese multi-word extraction demonstrate that AMI method hassuperior performance to traditional MI method. |
| Rights: | Copyright (C) 2009 ICIC International. Wen Zhang, Taketoshi Yoshida, Tu Bao Ho and Xijin Tang, International Journal of Innovative Computing, Information and Control, 5(2), 2009, 543-554. |
| URI: | http://hdl.handle.net/10119/9211 |
| 資料タイプ: | publisher |
| 出現コレクション: | a10-1. 雑誌掲載論文 (Journal Articles)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 13875.pdf | | 82Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
