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/10119/9052

タイトル: Adaptively entropy-based weighting classifiers in combination using Dempster-Shafer theory for word sense disambiguation
著者: Huynh, Van-Nam
Nguyen, Tri Thanh
Le, Cuong Anh
キーワード: Computational linguistics
Classifier combination
Word sense disambiguation
Dempster's rule of combination
Entropy
発行日: 2010-07
出版者: Elsevier
誌名: Computer Speech and Language
巻: 24
号: 3
開始ページ: 461
終了ページ: 473
DOI: 10.1016/j.csl.2009.06.003
抄録: In this paper we introduce an evidential reasoning based framework for weighted combination of classifiers for word sense disambiguation (WSD). Within this framework, we propose a new way of defining adaptively weights of individual classifiers based on ambiguity measures associated with their decisions with respect to each particular pattern under classification, where the ambiguity measure is defined by Shannon's entropy. We then apply the discounting-and-combination scheme in Dempster-Shafer theory of evidence to derive a consensus decision for the classification task at hand. Experimentally, we conduct two scenarios of combining classifiers with the discussed method of weighting. In the first scenario, each individual classifier corresponds to a well-known learning algorithm and all of them use the same representation of context regarding the target word to be disambiguated, while in the second scenario the same learning algorithm applied to individual classifiers but each of them uses a distinct representation of the target word. These experimental scenarios are tested on English lexical samples of Senseval-2 and Senseval-3 resulting in an improvement in overall accuracy.
Rights: NOTICE: This is the author's version of a work accepted for publication by Elsevier. Van-Nam Huynh, Tri Thanh Nguyen, Cuong Anh Le, Computer Speech and Language, 24(3), 2010, 461-473, http://dx.doi.org/10.1016/j.csl.2009.06.003
URI: http://hdl.handle.net/10119/9052
資料タイプ: author
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
14108-1.pdf195KbAdobe 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。

 


お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係