Artificial Intelligence
Natural language processing
Semantic web

Ontology-based document indexing

Student: Olivier Gagnon

Supervisor: Michel Desmarais

Co-supervisor(s): Michel Gagnon

The Web has existed for less than twenty years. Yet, it can be considered as one of the most important sources of information for the most varied of subjects, ranging from scientific research to the location of Vietnamese restaurants. Search engines such as Yahoo, Bing and Google improve regularly their algorithms in order to produce the best results for every possible query made by its users. Most popular search engines use indexing algorithms based on the presence (or not) of keywords corresponding to the query. This master’s thesis presents the experiences that have been made around the world for indexing Web documents with ontologies, which are directed graphs linking entities with relations that are widely used in the domain of Semantic Web. This document then presents an experience that attempts to demonstrate that an ontology-based indexing brings higher quality search results over a classic keyword-based indexing. This master’s thesis concludes with the results of the experience and potential improvements for ontology-based indexing.

For more information, click here