From: Tanabe, Lorrie (NIH/NLM/NCBI) [E]
Sent: Tuesday, April 04, 2006 10:37 AM
To: NLM/NCBI List ncbi-seminar
Subject: CBB Seminar

11 am Tuesday, April 4

NCBI Library B2


Lorrie Tanabe


CBB Seminar


Biomedical Named Entity Classification


We introduce a new approach to named entity classification which we term a Priority Model.
 We also describe the construction of a semantic database called SemCat consisting of a 
large number of semantically categorized names relevant to biomedicine. 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 compared 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.