Learn2Construct
Ahmed Khemiri, Amani Drissi, Anis Tissaoui, Salma Sassi, Richard Chbeir · 2021
In recent years, the research on Ontology Learning has become a hot topic among researchers because of the exponential increase of the number of documents and textual data not only on the web but also in digital libraries. This has participated to the emergence of new computational tools and methods to deal with the automatic organization, representation, retrieval and exploration of large corpus in order to have a good way of organizing and managing huge volumes of data. LDA-based approaches have proven to provide the best result [18][16] [4]. However, they suffers to several limitations related to concept and relation extraction, as well as coping with the corpus evolution. In order to cope with these problems, we propose here a new solution named Learn2Construct which is an automatic ontology construction method based on topic modeling. Experiments have been conducted to measure the effectiveness of our solution and compare it to existing ones. The results obtained are more than satisfactory.