Introducing MedCATTrainer, an Output from Our HDR UK National Text Analytics Project

Tom Searle and Zeljko Kraljevic have developed MedCATTrainer, an interface for building, improving and customising a given Named Entity Recognition and Linking (NER+L) model for biomedical domain text. MedCATTrainer offers an interactive web-interface to inspect and improve recognised entities from an underlying NER+L model via active learning.

MedCATTrainer is an output from our Health Data Research UK (HDR UK) National Text Analytics Project project lead by Professor Richard Dobson and Dr Angus Roberts.

Early output for the @HDR_UK Text Analytics National Implementation Project from Tom Searle @_kraljevic – ‘Free Text Annotation Interface with Active Learning and Research Use Case Specific Customisation’ https://t.co/xvrTohGkKAhttps://t.co/yUscOE1ufQ@cogstack #nlp #EHR https://t.co/msIhxFcOeJ

— Richard Dobson (@richdobson) August 9, 2019

Tom Searle also uploaded a video to YouTube highlighted MedCATTrainer submission process.

Read full paper here.

Photo credit: Pixabay/Pexel.