Cheap, Fast, and Good Enough for the Non-biomedical Domain but is It Usable for Clinical Natural Language Processing? Evaluating Crowdsourcing for Clinical Trial Announcement Named Entity Annotations.
Haijun ZhaiTodd LingrenLouise DelégerQi LiMegan KaiserLaura StoutenboroughImre SoltiPublished in: HISB (2012)
Keyphrases
- named entities
- clinical trials
- natural language processing
- genia corpus
- information extraction
- text mining
- medical domain
- named entity recognition
- question answering
- clinical practice
- relation extraction
- named entity extraction
- decision support system
- clinical guidelines
- electronic health records
- free text
- machine learning
- patient care
- co occurrence
- natural language
- wordnet
- annotated corpus
- text classification
- domain specific
- metadata
- cancer patients
- word sense disambiguation
- conditional random fields
- decision making
- semi supervised
- knowledge representation
- experimental design
- feature selection
- clinical decision support systems
- breast cancer patients