Extracting a sparsely located named entity from online HTML medical articles using support vector machine.
Jie ZouDaniel X. LeGeorge R. ThomaPublished in: DRR (2008)
Keyphrases
- named entities
- information extraction
- support vector machine
- named entity recognition
- named entity extraction
- text mining
- co occurrence
- relation extraction
- natural language processing
- news corpus
- question answering
- machine learning
- text documents
- noun phrases
- linguistic features
- web news
- unsupervised learning
- feature vectors
- support vector
- proper names
- training data
- maximum entropy model
- named entity disambiguation
- annotated corpus
- news articles
- object recognition
- image segmentation
- information retrieval