Research in Computing Science, Vol. 70, pp. 31-41, 2013.
Abstract: In this paper, we introduce a novel technique for named entity filtering, focused on the analysis of word association networks. We present an approach for modelling concepts which are distinctively related to specific named entity. We evaluated our approach in the context of the TREC Knowledge Base Acceleration track, and we obtained significantly better performance than the top-ranked systems. For this task, given the set of all named entities and nouns, our approach proved better-performing for named entity filtering than the baseline SVM classifier. This performance is the result of the ability to disambiguate entities, by taking into account the concepts relevant to a specific named entity.
PDF: Named Entity Filtering Based on Concept Association Graphs
PDF: Named Entity Filtering Based on Concept Association Graphs