A Priority Model for Named Entities

John Wilbur
(National Center for Biotechnology Information, National Library of Medicine)

We introduce a new approach to named entity classification which we term a Priority Model. We also describe the construction of a semantic data-base called SemCat consisting of a large number of names relevant to biomedicine together with data on their semantic categories. We used SemCat as training data to investigate name classification techniques. We generated a statistical language model and probabilistic context-free grammars for gene and protein name classification, and com-pared the results with the new model. For all three methods, we used a variable order Markov model to predict the nature of strings not represented in the training data. The Priority Model achieves an F-measure of 0.958-0.960, consistently higher than the statistical language model and probabilistic context-free grammar.