Andriy Mulyar
Andriy Mulyar
[MetaMapLite](https://academic.oup.com/jamia/article/24/4/841/2961848) looks promising - currently MetaMap is very bulk. This would be a fascinating direction to explore and would make the package much more robust.
**What problem does your feature solve?** A method to do analysis of annotations (namely for the application of looking at differences between gold and predicted annotations). **Describe the solution you'd...
The newest version of [Metamap now supports JSON format](https://metamap.nlm.nih.gov/Docs/FAQ/JSON.pdf) - update the [Metamap](https://github.com/NanoNLP/medaCy/blob/master/medacy/pipeline_components/metamap/metamap.py) wrapper to directly parse this information. It currently gathers the XML and manually turns it into JSON...
**Description** A CRF produces label probability outputs. Currently, we are simply using the highest probability label as the predicted entity label. It would be useful to allow for an option...
Currently only feature dictionaries exist - a necessity is the implementation of feature vectors. The feature type returned should be an argument to the FeatureExtractor class.
Each unit type will have its own lexicons to pull from. This is best accomplished by placing each unit type in its own pipeline component. This has been started to...
Currently, tokens are merged by default in components such as the MetaMap annotator or the various UnitAnnotators. This is so that annotated groups of tokens are seen as individual block...
#### Description I have a [study](https://www.openml.org/s/184) full of uploaded data benchmarks. I would like to create associated supervised classification tasks for each benchmark automatically; however, I have not been able...