Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorShanaz, A. L. F.-
dc.contributor.authorRagel, R.-
dc.identifier.citation8th International Symposium 2018 on “Innovative Multidisciplinary Research for Green Development”. 17th - 18th December, 2018. South Eastern University of Sri Lanka, University Park, Oluvil, Sri Lanka. pp. 205-225.en_US
dc.description.abstractThe aim of this paper is to implement an entity linking system for news recommendation. Which can automatically recognize Person entities (humans) from input English text (news article), and link them to the best-matched entities in Wikidata knowledge base. That is, for each specific mention of a person entity found in a text, the developed Named Entity Disambiguation (NED) algorithm was applied to search for candidate entities (in Wikidata) and return either the best candidate or a NIL reference if the spotted person entity does not match any Human in Wikidata. In a nutshell, our system maps mentions of ambiguous human names (people mention) in text onto Wikidata unique identifier (Q number). We extensively evaluated the performance of our system over manually annotated AIDA CoNLL-YAGO Dataset, and the experimental results show that our system achieves the top-5 precision of 84.4%.en_US
dc.publisherSouth Eastern University of Sri Lanka, University Park, Oluvil, Sri Lanka.en_US
dc.subjectNamed entity linkingen_US
dc.subjectNamed entity disambiguationen_US
dc.titleDisambiguation of human names in texten_US
Appears in Collections:8th International Symposium - 2018

Files in This Item:
File Description SizeFormat 
Full papers 1 - Page 221-233.pdf505.33 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.