The Allium prototype, developed by the RALI (Philippe Langlais, Fabrizio Gotti and Vincent Letard, Université de Montréal), aims to increase information discoverability in Érudit through the extraction of open information. It uses the semantics of the plain text of journal articles to explore the deep syntactic dependencies between the words of a sentence. The direct extraction of indexed facts allows to expand user experience and offers the possibility of browsing based on concepts, themes and named entities in context. The implementation of external links pointing to knowledge bases such as Wikipedia further enriches the browsing experience.
For example, by extracting the indexed fact “Sylvain L’Espérance is a documentary filmmaker” from a text, it will be possible to respond to the question “who are the contemporary documentary filmmakers interested in the issue of migration?”, as well as to establish a list of activist filmmakers or other thematic fact sheets.