Hello, cTAKES developing team,
We are using and comparing various NLP tools (including cTAKES) for processing
over 5 million clinical notes within Johns Hopkins Medical Institutes. As a
part of our comparisons, we are exploring the architecture of the NER and
(UMLS) concept linking components of the tools.
I was able to find the description on the cTAKES default/original dictionary
look up in the Savova et. al. 2010 paper but I was not able to find a paper or
tech report describing the fast UMLS dictionary lookup (Fast UMLS Processor)
Any description of the fast dictionary lookup algorithm is highly appreciated.
Masoud Rouhizadeh, PhD
NLP Specialist / Software Engineer
Institute for Clinical and Translational Research
Center for Clinical Data Analysis
School of Medicine, Johns Hopkins University