Resumo (PT):
This work aims at defining and evaluating different techniques to automa-
tically build temporal news sequences. The approach proposed is composed
by three steps: (i) near duplicate documents detention; (ii) keywords ex-
traction; (iii) news sequences creation. This approach is based on: Natural
Language Processing, Information Extraction, Name Entity Recognition and
supervised learning algorithms. The proposed methodology got a precision
of 93.1% for news chains sequences creation.
Abstract (EN):
This work aims at defining and evaluating different techniques to automa-
tically build temporal news sequences. The approach proposed is composed
by three steps: (i) near duplicate documents detention; (ii) keywords ex-
traction; (iii) news sequences creation. This approach is based on: Natural
Language Processing, Information Extraction, Name Entity Recognition and
supervised learning algorithms. The proposed methodology got a precision
of 93.1% for news chains sequences creation.
Idioma:
Português
Tipo (Avaliação Docente):
Científica
Notas:
Ebeling, Grønn, Hauge & Santos (eds.) Corpus-basedStudiesinContrastiveLinguistics
, Oslo Studies in Language 6(1), 2014. 1¿29. (ISSN 1890-9639)
http://www.journals.uio.no/osla
Nº de páginas:
29
Tipo de Licença: