Knowledge sharing using web mining for categorization and disambiguation of structured and unstructured data

Artigo de evento
Data de publicação
Proceedings of the European Conference on Knowledge Management, ECKM
Citações (Scopus)
da Silva L.R.
Omar N.
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
A new battle in the knowledge sharing revolves around technologies for absorption, disambiguation and enrichment of entities from a variety of sources of structured and unstructured data. It is known then that there are for some time several technical approaches for integrating unstructured knowledge from diverse sources. Today's computers, increasingly fast, and the explosion of Web data and improved software techniques are opening the door to rapid progress. Scientists at universities, government labs, Google, Microsoft, IBM and elsewhere are pursuing breakthroughs together, even if they are on different paths. As recurrent difficulty in several studies there is an urgent need to solve the task of linking an entity mention in the text to the real world counterpart in the existing knowledge base (entity-linking). This task is challenging once ambiguity, textual inconsistency, and lack of knowledge of the world in the knowledge base are concerned. And although many methods have been proposed to overcome this problem with different approaches, it remains opened to the general context of unstructured knowledge sharing. Thus, the alternative proposed in this paper considers the construction of knowledge sharing in a limited scope. The research objective is sharing knowledge based on structured and unstructured knowledge from the ontology integrated with the automated and self-managed and in largescale extraction, also with the analysis of user interaction. The method is based in "Knowledge-Discovery in Databases" method for structured data and is intended to use "Ontology Web Language" as a formal language to deal with unstructured data, allied with user interactions. This work has been developed over the last two years, and this disclosure is intended to present preliminary results obtained from the use of tools for the automatic extraction and knowledge sharing.
Assuntos Scopus
Automatic extraction , Knowledge discovery in database , Knowledge-sharing , Ontology web language , Research objectives , Sharing knowledge , Software techniques , Web ontology language