TF-IDF vs Word Embeddings for Morbidity Identification in Clinical Notes: An Initial Study.
Danilo DessìRim HelaouiVivek KumarDiego Reforgiato RecuperoDaniele RiboniPublished in: SmartPhil@IUI (2020)
Keyphrases
- tf idf
- term frequency
- term weighting
- stop words
- weighting scheme
- inverse document frequency
- information retrieval
- vector space model
- document clustering
- retrieval model
- text documents
- document frequency
- text categorization
- vector space
- ranking algorithm
- n gram
- co occurrence
- keywords
- clustering method
- text classification
- average precision
- knowledge discovery
- data points
- training data
- feature selection