Word sense disambiguation by information filtering and extraction

被引：3

作者：

Ellman, J ^{[1
]}

Klincke, I ^{[1
]}

Tait, J ^{[1
]}

机构：

[1] Univ Sunderland, Sch Comp & Informat Syst, Sunderland SR2 7EE, Durham, England

来源：

COMPUTERS AND THE HUMANITIES | 2000年 / 34卷 / 1-2期

关键词：

word sense disambiguation; information filtering; SENSEVAL;

D O I：

10.1023/A:1002423406899

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We describe a simple approach to word sense disambiguation using information filtering and extraction. The method fully exploits and extends the information available in the Hector dictionary. The algorithm proceeds by the application of several filters to prune the candidate set of word senses returning the most frequent if more than one remains. The experimental methodology and its implication are also discussed.

引用

页码：127 / 134

页数：8

共 13 条

[1]

[Anonymous], P 1975 WORKSH THEOR

[2]

[Anonymous], 1992, P 3 C APPL NAT LANG

[3]

ELLMAN J, IN PRESS U SUNDERLAN

[4]

ELLMAN J, 1997, UK IEE C INT WORLD W

[5]

Morris J., 1991, Computational Linguistics, V17, P21

[6]

OKUMURA M, P COLING 1994, V2, P755

[7]

ONYSHKEVYCH B, 1993, P 5 MESS UND C MUC 5

[8] INFORMATION EXTRACTION AS A BASIS FOR HIGH-PRECISION TEXT CLASSIFICATION [J].

RILOFF, E ;

LEHNERT, W .

ACM TRANSACTIONS ON INFORMATION SYSTEMS, 1994, 12 (03) :296-333

[9]

SALTON G, INTRO MODERN INFORMA

[10]

St-Onge D., 1995, THESIS U TORONTO

← 1 2 →