A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools.
Karin VerspoorKevin Bretonnel CohenArrick LanfranchiColin WarnerHelen L. JohnsonChristophe RoederJinho D. ChoiChristopher S. FunkYuriy MalenkiyMiriam EckertNianwen XueWilliam A. Baumgartner Jr.Michael BadaMartha PalmerLawrence E. HunterPublished in: BMC Bioinform. (2012)
Keyphrases
- journal articles
- natural language processing
- software tools
- medical literature
- text mining
- metadata
- information extraction
- machine learning
- life sciences
- national library of medicine
- natural language
- wordnet
- medical subject headings
- entity extraction
- information retrieval systems
- named entity recognition
- text processing
- free text
- machine learning methods
- artificial intelligence
- data mining