PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts.
Franck DernoncourtJi Young LeePublished in: IJCNLP(2) (2017)
Keyphrases
- benchmark datasets
- evidence based medicine
- support vector
- support vector machine svm
- classification accuracy
- decision trees
- uci datasets
- classification algorithm
- feature vectors
- feature extraction
- biomedical literature
- supervised learning
- training dataset
- automatic classification
- natural language
- pattern recognition
- classification method
- machine learning
- medical domain
- training set
- medical images
- feature set
- multi class
- information extraction
- support vector machine