File(s) under permanent embargo
A hybrid model for named entity recognition using unstructured medical text
conference contribution
posted on 2014-01-01, 00:00 authored by Sara Keretna, Chee Peng LimChee Peng Lim, Douglas CreightonDouglas CreightonNamed entity recognition (NER) is an essential step in the process of information extraction within text mining. This paper proposes a technique to extract drug named entities from unstructured and informal medical text using a hybrid model of lexicon-based and rule-based techniques. In the proposed model, a lexicon is first used as the initial step to detect drug named entities. Inference rules are then deployed to further extract undetected drug names. The designed rules employ part of speech tags and morphological features for drug name detection. The proposed hybrid model is evaluated using a benchmark data set from the i2b2 2009 medication challenge, and is able to achieve an f-score of 66.97%.
History
Event
IEEE International System of Systems Engineering. Conference (9th : 2014 : Adelaide, South Australia)Pagination
85 - 90Publisher
IEEELocation
Adelaide, South AustraliaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2014-06-09End date
2014-06-13ISBN-13
9781479952274Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2014, IEEEEditor/Contributor(s)
S Cook, V Ireland, A Gorod, T Ferris, Q DoTitle of proceedings
SOSE 2014 : The Socio-Technical Perspective : Proceedings of the 9th International Conference on System of Systems EngineeringUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC