Recherche d'information sémantique et extraction automatique d'ontologie du domaine
|Abstract:||It can prove to be diffcult, even for a small size organization, to find information among hundreds, even thousands of electronic documents. Most often, the methods employed by search engines on the Internet are used by companies wanting to improve information retrieval on their intranet. These techniques rest on statistical methods and do not make it possible neither to evaluate the semantics contained in the user requests, nor in the documents. Certain methods were developed to extract this semantics and thus, to improve the answer given to requests. On the other hand, the majority of these techniques were conceived to be applied on the entire World Wide Web and not on a particular field of knowledge, like corporative data. It could be interesting to use domain specific ontologies in trying to link a specific query to related documents and thus, to be able to better answer these queries. This thesis presents our approach which proposes the use of the Text-To-Onto software to automatically create an ontology describing a particular field. Thereafter, this ontology is used by the Sesei software, which is a semantic filter for conventional search engines. This method makes it possible to improve the relevance of documents returned to the user.|
|Document Type:||Mémoire de maîtrise|
|Open Access Date:||12 April 2018|
|Collection:||Thèses et mémoires|
All documents in CorpusUL are protected by Copyright Act of Canada.