swfarnsworth
commented
4 years ago MedaCy is intended to be strictly for named entity recognition, with the intention that it can be integrated into end-to-end solutions that require named entity recognition as a component. I'm not sure that predicting subsequent tokens is sufficiently related to that goal for it to need to be included here.
What problem does your feature solve? can you add Language model for medical notes to predict next word
Describe the solution you'd like adding transformer model , or implementation of the paper Learning to Write Notes in Electronic Health Records