Named entity recognition and normalization: A domain-specific language approach

Abstract

We present, RNer, a tool that performs Named Entity Recognition and Normalization of gene and protein mentions on biomedical text. The tool we present not only offers a complete solution to the problem, but it does so by providing easily configurable framework, that abstracts the algorithmic details from the domain specific. Configuration and tuning for particular tasks is done using domain specific languages, clearer and more succinct, yet equally expressive that general purpose languages. An evaluation of the system is carried using the BioCreative datasets. © 2009 Springer-Verlag Berlin Heidelberg.