In this paper we present an unsupervised model for learning arbitrary relations between concepts of a molecular biology ontology for the purpose of supporting text mining and manual ontology build- ing. Relations between named-entities are learned from the GENIA corpus by means of several stan- dard natural language processing techniques. An in-depth analysis of the output of the system shows that the model is accurate and has good potentials for text mining and ontology building applications.
Unsupervised Learning of Semantic Relations between Concepts of a Molecular Biology Ontology
Contributo in atti di convegno
ACM Press, New York, USA
Nineteenth International Joint Conference on Artificial Intelligence (IJCAI-05), pp. 659–664, Edinburgh, 2005