Training Set Expansion Using Word Embeddings for Korean Medical Information Extraction.
Young-Min KimPublished in: Poly/DMAH@VLDB (2019)
Keyphrases
- information extraction
- training set
- word sense disambiguation
- natural language text
- natural language processing
- test set
- word order
- training data
- medical domain
- machine translation
- machine translation system
- text mining
- free text
- precision and recall
- classification accuracy
- cross validation
- supervised learning
- named entities
- nearest neighbor
- training examples
- named entity recognition
- co occurrence
- target word
- active learning
- training samples
- structured data
- target language
- classification algorithm
- data sets
- vector space
- medical diagnosis
- n gram
- conditional random fields
- test data
- question answering
- decision trees
- natural language
- manifold learning
- information retrieval
- text summarization
- relation extraction
- morphological analysis
- euclidean space
- text documents
- wordnet
- keywords
- test images
- medical imaging
- class labels
- high dimensional data
- distance measure
- support vector machine
- feature space