| Authors: |
Yang Wang
and Haofen Wang
and Haiping Zhu
and Yong Yu
|
| URL: |
http://dx.doi.org/10.1007/978-3-540-73351-5_5 |
| Description: |
SpringerLink - Book Chapter |
| Tags: |
imported
recommendersystems
wikipedia
|
| Abstract: |
Compared with plain-text resources, the ones in âsemi-semanticâ web sites, such as Wikipedia, contain high-level semantic
information which will benefit various automatically annotating tasks on themself. In this paper, we propose a âcollaborativeannotatingâ approach to automatically recommend categories for a Wikipedia article by reusing category annotations from itsmost similar articles and ranking these annotations by their confidence. In this approach, four typical semantic featuresin Wikipedia, namely incoming link, outgoing link, section heading and template item, are investigated and exploited as therepresentation of articles to feed the similarity calculation. The experiment results have not only proven that these semanticfeatures improve the performance of category annotating, with comparison to the plain text feature; but also demonstratedthe strength of our approach in discovering missing annotations and proper level ones for Wikipedia articles. |
@article{keyhere,
title = {Exploit Semantic Information for Category Annotation Recommendation in Wikipedia},
author = {Yang Wang and Haofen Wang and Haiping Zhu and Yong Yu},
journal = {Natural Language Processing and Information Systems},
pages = {48--60},
url = {http://dx.doi.org/10.1007/978-3-540-73351-5_5},
year = {2007},
description = {SpringerLink - Book Chapter},
abstract = {Compared with plain-text resources, the ones in âsemi-semanticâ web sites, such as Wikipedia, contain high-level semantic
information which will benefit various automatically annotating tasks on themself. In this paper, we propose a âcollaborativeannotatingâ approach to automatically recommend categories for a Wikipedia article by reusing category annotations from itsmost similar articles and ranking these annotations by their confidence. In this approach, four typical semantic featuresin Wikipedia, namely incoming link, outgoing link, section heading and template item, are investigated and exploited as therepresentation of articles to feed the similarity calculation. The experiment results have not only proven that these semanticfeatures improve the performance of category annotating, with comparison to the plain text feature; but also demonstratedthe strength of our approach in discovering missing annotations and proper level ones for Wikipedia articles.},
keywords = {imported recommendersystems wikipedia }
}
::