Effect of word sets with non-taxonomical relation for retrieval support

被引：0
|
作者：
Yamamoto, Eiko [1 ]
Isahara, Hitoshi [1 ]
机构：
[1] Natl Inst Informat & Commun Technol, Computat Linguist Grp, 3-5 Hikaridai,Seika Cho, Kyoto 6190289, Japan
来源：
PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND KNOWLEDGE ENGINEERING (NLP-KE'07) | 2007年
关键词：
D O I：
10.1109/NLPKE.2007.4368063
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
At least two kinds of relations exist among related words: the taxonomical relation and the thematic relation. However, although words with a taxonomical relation arc easy to identify from linguistic resources such as dictionaries and thesauri, words with a thematic relation are difficult to identify because they are rarely maintained in linguistic resources. In this paper, we present a method of extracting thematically (nontaxonomically) related word sets among words for retrieval support by employing case-marking articles derived from syntactic analysis. For verifying the capability of such word sets, we compared the results retrieved with words related only taxonomically and those retrieved with words including a word related non-taxonomically to the other words. We found additional term which is thematically related to other terms is effective at retrieving informative pages.
引用
收藏
页码：407 / +
页数：2
相关论文
共 50 条
12345