dc.contributor.author | Roalkvam, Brage Michael E. | |
dc.date.accessioned | 2015-09-11T11:36:28Z | |
dc.date.available | 2015-09-11T11:36:28Z | |
dc.date.issued | 2015-06 | |
dc.identifier.uri | http://hdl.handle.net/11250/299622 | |
dc.description | Master's thesis in Computer science | nb_NO |
dc.description.abstract | This master's thesis presents an entity-linking tool for detecting entity-bearing words
in news articles and linking them to the corresponding entries in a knowledge base.
Given the vast volume of news articles produced every day, such a tool needs to be not
only effective but also effcient. The approach consists of three steps. First, entities
are spotted on the basis of capitalized (uppercase) letters in words. Next, entities with
surface forms matching the mention are considered. Finally, in the disambiguation phase,
a new method based on local relatedness is employed. Using the Entity Recognition and
Disambiguation 2014 Challenge platform, we demonstrate that the efficiency of this
solution is competitive with other available methods. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | University of Stavanger, Norway | nb_NO |
dc.relation.ispartofseries | Masteroppgave/UIS-TN-IDE/2015; | |
dc.subject | informasjonsteknologi | nb_NO |
dc.subject | datateknikk | nb_NO |
dc.subject | entity linking | nb_NO |
dc.subject | Freebase | nb_NO |
dc.subject | Java | nb_NO |
dc.title | Effective entity linking for news articles | nb_NO |
dc.type | Master thesis | nb_NO |
dc.subject.nsi | VDP::Technology: 500::Information and communication technology: 550::Computer technology: 551 | nb_NO |