search

healtex / texscrubber

Personal information de-identification tool
Apache License 2.0
2 stars 2 forks source link

NamedEntityExtractor component #4

Closed mbelousov closed 7 years ago

mbelousov commented 7 years ago

Extracts all named entities from unannotated GATEDocument and generates annotated GATEDocument

dehghana commented 7 years ago

Assuming this issue is: Applying DEID NERs on an unannotated gate.Document and generate annotated gate.Document

hkkenneth commented 7 years ago

@dehghana To start integrating this GATE pipeline with Spring batch, can we call this extractor from FirstPassItemProcessor.process() to make sure it can run?

Let's keep the dummy output of processor unchanged for now. Based on this integration, I can then make the transition to gate.GATEDocument so that other people can work on the rest of the pipeline.