Disambiguating named entities by semantic web

DOI

10.2991/csss-14.2014.173How to use a DOI?

Keywords

linked open data, named entity disambiguation, natural language processing, semantic web

Abstract

There are many words in natural language sentences which describe an object or event in real world. An important step to understand a sentence is finding the exact meaning of all words. In this paper we propose an approach to identify meaning of each named entity of a text by using web of data (LOD) as a large scale knowledge base. The proposed approach is referencing named entities to suitable URIs of web of data. It compares the context of the text with RDF graphs retrieved from the web and then select URIs which have maximum agreement with named entities of the text. Experimental Results show that our approach outperforms previous works in terms of accuracy and Precision on Wikipedia articles.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Azari Ideh
AU  - Koohpeyma Fateme
PY  - 2014/06
DA  - 2014/06
TI  - Disambiguating named entities by semantic web
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 741
EP  - 744
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.173
DO  - 10.2991/csss-14.2014.173
ID  - Ideh2014/06
ER  -