Clustering Large-scale Diverse Electronic Medical Records to Aid Annotation for Generic Named Entity Recognition.
Nithin HaridasYubin KimPublished in: HSDM@WSDM (2020)
Keyphrases
- named entity recognition
- annotated corpus
- information extraction
- named entities
- natural language processing
- electronic medical record
- semi supervised
- maximum entropy
- text summarization
- conditional random fields
- relation extraction
- clustering algorithm
- k means
- automatic annotation
- unsupervised learning
- active learning
- medical records
- real world
- medical data
- graphical models
- domain specific
- co occurrence
- question answering
- medical images
- open source
- patient data
- text mining
- computer vision
- machine learning