File(s) under permanent embargo
Enhancement of medical named entity recognition using graph-based features
conference contribution
posted on 2015-01-01, 00:00 authored by Sara Keretna, Chee Peng LimChee Peng Lim, Douglas CreightonDouglas CreightonNamed Entity Recognition (NER) is a crucial step in text mining. This paper proposes a new graph-based technique for representing unstructured medical text. The new representation is used to extract discriminative features that are able to enhance the NER performance. To evaluate the usefulness of the proposed graph-based technique, the i2b2 medication challenge data set is used. Specifically, the 'treatment' named entities are extracted for evaluation using six different classifiers. The F-measure results of five classifiers are enhanced, with an average improvement of up to 26% in performance.
History
Event
IEEE International Conference on Systems, Man, and Cybernetics (2015 : Hong Kong, China)Pagination
1895 - 1900Publisher
IEEELocation
Hong Kong, ChinaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2015-10-09End date
2015-10-12ISSN
1062-922XISBN-13
9781479986965Publication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2015, IEEETitle of proceedings
SMC 2015 : Big Data Analytics for Human-Centric Systems. Proceedings of the 2015 IEEE International Conference on Systems, Man, and CyberneticsUsage metrics
Categories
No categories selectedKeywords
Science & TechnologyTechnologyComputer Science, CyberneticsComputer Science, Information SystemsComputer Science, Theory & MethodsComputer ScienceMachine learningconditional random fieldbiomedical named entity recognitioninformation extractionmedical text miningTEXTIDENTIFICATIONCONSTRUCTIONCLASSIFIEREngineering, Electrical & ElectronicTelecommunicationsEngineering
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC