cTAKES+UMLS+Package+Fetcher - apache/ctakes GitHub Wiki

Introduction

The default cTAKES method for Named Entity Recognition (NER) is running the cTAKES Fast Dictionary Lookup algorithm on notes.
By default, cTAKES Fast Dictionary Lookup uses a subset of the Unified Medical Language System (UMLS). The default dictionary is not part of the Apache cTAKES distributed package, and must be obtained separately. To make this process easier for the user, there is a utility GUI named the UMLS Package Fetcher.

Step-by-step guide

  1. Obtain a license for the Unified Medical Language System (UMLS)

  2. Open the UMLS Package Fetcher GUI ... execute bin/getUmlsDictionary

  • The window will be mostly empty as no actions to download have been taken.



  1. Click the Download Dictionary button. (Crate with green arrow)
  • The dictionary will be downloaded and placed in the appropriate location for use with cTAKES.
⚠️ **GitHub.com Fallback** ⚠️