Using distributional similarity to organise biomedical terminology.

The article studies an application of distributional similarity techniques to the problem of structural organization of biomedical terminology. The application domain is the relatively small GENIA corpus. Using terms that have been accurately marked-up by hand within the corpus, the problem of automatically determining semantic proximity is considered. Terminological units are defined as normalized classes of individual terms. Syntactic analysis of the corpus data is carried out using the Pro3Gres parser and provides the data required to calculate distributional similarity using a variety of measures. Evaluation is performed against a hand-crafted gold standard for this domain in the form of the GENIA ontology. The paper shows that distributional similarity can be used to predict semantic type with a good degree of accuracy, reaching an optimal value of 63.1 percent.