• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 2
  • Tagged with
  • 2
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Um modelo híbrido para o WSD em biomedicina

Goulart, Rodrigo Rafael Vilarreal January 2013 (has links)
Made available in DSpace on 2013-08-07T18:43:20Z (GMT). No. of bitstreams: 1 000448850-Texto+Completo-0.pdf: 2763654 bytes, checksum: 430bc12ce50b74821fe6a8aa37994260 (MD5) Previous issue date: 2013 / This work studies Word Sense Disambiguation (WSD) in the Biomedicine domain for English language, using external knowledge sources. Among the existing proposals for the selection of a sense for an ambiguous word, there is the graph-based approach. This approach uses a metric in the evaluation of graphs containing candidates to the correct sense for the ambiguous word. In this research, a set of metrics is analyzed individually, and, based on this evaluation, we propose a hybrid model for the selection of the metrics in order to determine the most adequate metric to be employed. The model makes use of a set of features and heuristics that determine a semi-supervised solution for WSD. The results obtained with experiments show an improvement in performance and reveal new perspectives of research. The proposed model raises the hit rate to 68,48%, increasing significantly in 3,52% the rate reported in literature. / Este trabalho estuda o Word Sense Disambiguation no domínio da Biomedicina, para a língua inglesa, com uso de fontes externas de conhecimento. Dentre as propostas existentes para a seleção de um sentido para uma palavra ambígua, está a abordagem baseadas em grafos. Essa abordagem emprega uma métrica na avaliação de grafos que contêm candidatos ao sentido correto da palavra ambígua. Nesta pesquisa um conjunto de métricas é analisado individualmente e, com base nas avaliações, propõe-se um modelo híbrido de seleção de métricas com o objetivo de determinar a métrica mais adequada a ser empregada. O modelo faz uso de um conjunto de features e heurísticas que determinam uma solução semi-supervisionada para o WSD. Os resultados obtidos com experimentos apontam melhoria na performance e revelam novas perspectivas de pesquisa. O modelo proposto eleva a taxa de acerto a 68,48%, aumentando significativamente em 3,52% a taxa reportada na literatura.
2

Um modelo h?brido para o WSD em biomedicina

Goulart, Rodrigo Rafael Vilarreal 26 March 2013 (has links)
Made available in DSpace on 2015-04-14T14:50:02Z (GMT). No. of bitstreams: 1 448850.pdf: 2763654 bytes, checksum: 430bc12ce50b74821fe6a8aa37994260 (MD5) Previous issue date: 2013-03-26 / This work studies Word Sense Disambiguation (WSD) in the Biomedicine domain for English language, using external knowledge sources. Among the existing proposals for the selection of a sense for an ambiguous word, there is the graph-based approach. This approach uses a metric in the evaluation of graphs containing candidates to the correct sense for the ambiguous word. In this research, a set of metrics is analyzed individually, and, based on this evaluation, we propose a hybrid model for the selection of the metrics in order to determine the most adequate metric to be employed. The model makes use of a set of features and heuristics that determine a semi-supervised solution for WSD. The results obtained with experiments show an improvement in performance and reveal new perspectives of research. The proposed model raises the hit rate to 68,48%, increasing significantly in 3,52% the rate reported in literature / Este trabalho estuda o Word Sense Disambiguation no dom?nio da Biomedicina, para a l?ngua inglesa, com uso de fontes externas de conhecimento. Dentre as propostas existentes para a sele??o de um sentido para uma palavra amb?gua, est? a abordagem baseadas em grafos. Essa abordagem emprega uma m?trica na avalia??o de grafos que cont?m candidatos ao sentido correto da palavra amb?gua. Nesta pesquisa um conjunto de m?tricas ? analisado individualmente e, com base nas avalia??es, prop?e-se um modelo h?brido de sele??o de m?tricas com o objetivo de determinar a m?trica mais adequada a ser empregada. O modelo faz uso de um conjunto de features e heur?sticas que determinam uma solu??o semi-supervisionada para o WSD. Os resultados obtidos com experimentos apontam melhoria na performance e revelam novas perspectivas de pesquisa. O modelo proposto eleva a taxa de acerto a 68,48%, aumentando significativamente em 3,52% a taxa reportada na literatura

Page generated in 0.0157 seconds