A New Data Representation Based on Training Data Characteristics to Extract Drug Named-Entity in Medical Text.
Sadikin MujionoMohamad Ivan FananyChan BasaruddinPublished in: CoRR (2016)
Keyphrases
- data representation
- named entities
- training data
- text mining
- text documents
- proper names
- named entity disambiguation
- noun phrases
- named entity recognizer
- information extraction
- named entity recognition
- co occurrence
- named entity extraction
- relation extraction
- question answering
- natural language processing
- dimensionality reduction
- data representations
- learning algorithm
- xml documents
- automatic extraction
- training set
- decision trees
- information retrieval
- unsupervised learning
- supervised learning
- relational databases
- annotated corpus
- data sets
- domain knowledge
- xml schema
- high dimensional
- reinforcement learning