Natural Language Processing Lab
CHIP NLP Software
Our goal is to create an open source end-to-end system for extracting information from the clinical narrative part of the Electronic Health Record. Components of this system include many core Natural Language Processing tasks. Here at Children's Hospital Boston/Harvard Medical School our focus is on the general task of semantic processing, with a focus on normalization to standards and community-adopted conventions. Specifically this involves work on components for relation extraction, coreference resolution, constituency parsing, named entity recognition, temporal relation extraction, and others. For more information see publications and partners at left.
Our end-to-end system is called cTAKES (clinical Text And Knowledge Extraction System). cTAKES is built on the UIMA engineering framework, also used by IBM's "Watson" question answering system. cTAKES is released open source under the Apache License and is available for download at its Sourceforge site