Made available in DSpace on 2015-04-14T14:49:58Z (GMT). No. of bitstreams: 1
446187.pdf: 2000156 bytes, checksum: d69c6168cd6efd48f1f38ca794de2813 (MD5)
Previous issue date: 2012-12-11 / The construction of ontologies is a complex process that includes steps such as extraction of domain concepts, as well as the extraction of taxonomic and non-taxonomic relations between these concepts. The step of extracting non-taxonomic relations is the most neglected, specially for texts in portuguese. This dissertation presents a proposal for extracting non-taxonomic relations from texts in portuguese (corpora). These texts are represented by a list of domain concepts and contextual informations extracted by the tool ExATOlp. An application of the proposed process was performed with corpora of five domains and analysis on the relevance of the concepts, the specificity of relations and relations extracted application was made. Through this analysis, the proposed process seemed to be relevant and is considered the main contribution of this dissertation. Additionally, a tool for visualizing the extracted non-taxonomic relations, useful for various linguistic applications, is also proposed. / A constru??o de ontologias ? um processo complexo que compreende etapas como a extra??o de conceitos de dom?nio, bem como a extra??o de rela??es taxon?micas e n?o-taxon?micas entre esses conceitos. A etapa de extra??o de rela??es n?o-taxon?micas ? a mais negligenciada, especialmente para textos na l?ngua portuguesa. Essa disserta??o apresenta uma proposta de extra??o de rela??es n?o-taxon?micas a partir de textos em l?ngua portuguesa (corpora). Esses textos s?o representados por uma lista de conceitos e informa??es contextuais automaticamente extra?dos pela ferramenta ExATOlp. Uma aplica??o do processo proposto foi realizada com corpora de cinco dom?nios e uma an?lise sobre a relev?ncia dos conceitos, a especifidade das rela??es e a aplica??o das rela??es extra?das foi realizada. Atrav?s dessa an?lise o processo proposto mostrou-se relevante, sendo considerado a principal contribui??o dessa disserta??o. Adicionalmente, uma ferramenta para visualiza??o das rela??es n?o-taxon?micas extra?das, ?til para diversas aplica??es lingu?sticas, tamb?m ? proposta.
| Identifer | oai:union.ndltd.org:IBICT/oai:tede2.pucrs.br:tede/5207 |
| Date | 11 December 2012 |
| Creators | Ferreira, Vinicius Hartmann |
| Contributors | Vieira, Renata |
| Publisher | Pontif?cia Universidade Cat?lica do Rio Grande do Sul, Programa de P?s-Gradua??o em Ci?ncia da Computa??o, PUCRS, BR, Faculdade de Inform?ca |
| Source Sets | IBICT Brazilian ETDs |
| Language | Portuguese |
| Detected Language | English |
| Type | info:eu-repo/semantics/publishedVersion, info:eu-repo/semantics/masterThesis |
| Format | application/pdf |
| Source | reponame:Biblioteca Digital de Teses e Dissertações da PUC_RS, instname:Pontifícia Universidade Católica do Rio Grande do Sul, instacron:PUC_RS |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | 1974996533081274470, 500, 600, 1946639708616176246 |
Page generated in 0.0022 seconds