PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts.
Franck DernoncourtJi Young LeePublished in: CoRR (2017)
Keyphrases
- benchmark datasets
- evidence based medicine
- automatic classification
- classification accuracy
- pattern recognition
- uci datasets
- biomedical literature
- feature space
- medical diagnosis
- feature set
- image classification
- training dataset
- machine learning
- class labels
- support vector machine svm
- classification method
- natural language
- support vector
- decision trees
- classification algorithm
- semantic network
- supervised learning
- medical data
- feature vectors
- feature selection