The Simple Semantic Classifier is designed to take one or more ontologies or other controlled vocabularies in OBO format, plus a natural language text, as input, and return a broad semantic class for the input text. Input texts are meant to be small, on the order of phrases; for instance, a noun phrase, or a verb chunk. The "broad semantic classes" each correspond to one of the input ontologies, so the task of class assignment is roughly similar to deciding which semantic domains the input should be assigned to, where "semantic domain" corresponds to an ontology--if the input text were to be assigned to an ontology, which of the ontologies (if any) would it be?
K. Bretonnel Cohen, Thomas Christiansen, William A. Baumgartner Jr., Karin Verspoor, and Lawrence E. Hunter (2011) Fast and simple semantic class assignment for biomedical text. BioNLP 2011, pp. 38-45.
It is one of the projects of the BioNLP initiative by the Center for Computational Pharmacology
at the University of Colorado Denver Health Sciences Center
to create and distribute code, software, and data for applying natural language
processing techniques to biomedical texts.