A framework for supporting knowledge representation – an ontological based approach

• Author(s): Figueiras, Paulo Alves
• Date: 2012
• Persistent ID: http://hdl.handle.net/10362/7576
• Origin: Repositório Institucional da UNL
• Subject(s): Knowledge representation; Semantic web; Information retrieval; Ontology engineering; Vector-space model
• Document Type: Master thesis
• Language: English
• Advisor(s): Gonçalves, Ricardo; Lima, Celson
• Contributor(s): RUN

Description

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica e de Computadores

The World Wide Web has had a tremendous impact on society and business in just a few years by making information instantly available. During this transition from physical to electronic means for information transport, the content and encoding of information has remained natural language and is only identified by its URL. Today, this is perhaps the most significant obstacle to streamlining business processes via the web. In order that processes may execute without human intervention, knowledge sources, such as documents, must become more machine understandable and must contain other information besides their main contents and URLs. The Semantic Web is a vision of a future web of machine-understandable data. On a machine understandable web, it will be possible for programs to easily determine what knowledge sources are about. This work introduces a conceptual framework and its implementation to support the classification and discovery of knowledge sources, supported by the above vision, where such sources’ information is structured and represented through a mathematical vector that semantically pinpoints the relevance of those knowledge sources within the domain of interest of each user. The presented work also addresses the enrichment of such knowledge representations, using the statistical relevance of keywords based on the classical vector space model concept, and extending it with ontological support, by using concepts and semantic relations, contained in a domain-specific ontology, to enrich knowledge sources’ semantic vectors. Semantic vectors are compared against each other, in order to obtain the similarity between them, and better support end users with knowledge source retrieval capabilities.