arXiv subjects
Publications and source records attributed to Frédérique Laforest.
Converting property graphs to RDF graphs allows to enhance the interoperability of knowledge graphs. But existing tools perform the same conversion for every graph, regardless of its content. In this paper, we propose PREC, a user-configured conversion of property graphs to RDF graphs to better capture the semantics of the content.
While Wikipedia exists in 287 languages, its content is unevenly distributed among them. In this work, we investigate the generation of open domain Wikipedia summaries in underserved languages using structured data from Wikidata. To this end, we propose a neural network architecture equipped with copy actions that learns to generate single-sentence and comprehensible textual summaries from Wikidata triples. We demonstrate the effectiveness of the proposed approach by evaluating it against a set of baselines on two languages of different natures: Arabic, a morphological rich language with a larger vocabulary than English, and Esperanto, a constructed language known for its easy acquisition.