Disambiguating named entities by semantic web
Azari Ideh, Koohpeyma Fateme · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2014
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.