Detalhes bibliográficos
Ano de defesa: |
2015 |
Autor(a) principal: |
Pires, Julio Cesar Batista
|
Orientador(a): |
Carvalho, Cedric Luiz de
|
Banca de defesa: |
Carvalho, Cedric Luiz de,
Ambrósio, Ana Paula Laboissière,
Vieira, Renata |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Federal de Goiás
|
Programa de Pós-Graduação: |
Programa de Pós-graduação em Ciência da Computação (INF)
|
Departamento: |
Instituto de Informática - INF (RG)
|
País: |
Brasil
|
Palavras-chave em Português: |
|
Palavras-chave em Inglês: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
http://repositorio.bc.ufg.br/tede/handle/tede/4723
|
Resumo: |
Many people are constantly connected on the Web. They are looking for all kinds of things. The Web is a huge source of information. So, they can find almost everything they want. However, Web information is disorganized and have no formal structure. This hampers machine processing and consequently makes information access more difficult. Bringing structure to the Web can be one of the key points for facilitating user searching and navigation. A recent technique, Open Information Extraction, has been successfully applied to extract structured information from the Web. This technique has been mostly applied in pages written in English. This work is specifically focused on information extraction for Portuguese. Techniques used here can be also used to other languages too. |