earticle

영어

In this paper, we present the ideas and methodologies on labeling the mentioned entities with the wiki dataset. This paper presents a system for the recognition and semantic disambiguation of named entities based on information extracted from a large encyclopedic collection from Wikipedia. We focus on maximizing the similarity between the contextual information extracted from Wikipedia and the context of a document, as well as the similarity among the category tags associated with the candidate entities. Our experimental results show that the proposed methods are effective and efficient to answer complex named entities disambiguation over the Wikipedia dataset.