The academic paper “BiOnt: Deep Learning using Multiple Biomedical Ontologies for Relation Extraction”, co-authored by Diana Sousa and Francisco M. Couto (LASIGE researchers), was accepted at the 42nd European Conference on Information Retrieval (ECIR 2020).

The paper describes BiOnt in detail, as a system to perform relation extraction, the deep learning system, BiOnt, employs four types of biomedical ontologies, namely, the Gene Ontology, the Human Phenotype Ontology, the Human Disease Ontology, and the Chemical Entities of Biological Interest, regarding gene-products, phenotypes, diseases, and chemical compounds, respectively.

The prototype is available here.