Ontology-based semantic annotation: an automatic hybrid rule-based method

Sondes Bannour (1) , Laurent Audibert (1) , Henry Soldano (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord

In the perspective of annotating a text with respect to an ontology, we have partici-pated in the subtask 1 of the BB BioNLP-ST whose aim is to detect, in the text, Bacteria Habitats and associate to them one or several categories from the Onto-Biotope ontology provided for the task. We have used a rule-based machine learn-ing algorithm (WHISK) combined with a rule-based automatic ontology projection method and a rote learning technique. The combination of these three sources of rules leads to good results with a SER measure close to the winner and a best F-measure.

Domaines: Informatique et langage [cs.CL]

Sondes Bannour, Laurent Audibert, Henry Soldano. Ontology-based semantic annotation: an automatic hybrid rule-based method. ACL 2013, Aug 2013, Sofia, Bulgaria. pp.139 - 143. ⟨hal-01074936⟩