Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Named entity recognition with combinations of conditional random fields

 
: Klinger, R.; Friedrich, C.M.; Fluck, J.; Hofmann-Apitius, M.

:
Volltext urn:nbn:de:0011-n-574949 (58 KByte PDF)
MD5 Fingerprint: c4b0ac325b2a0c41d6e063909893ddf2
Erstellt am: 27.6.2012


Valencia, A.:
Second BioCreative Challenge Evaluation Workshop 2007. Proceedings : Critical Assessment of Information Extraction in Molecular Biology, April 23-25 2007, Madrid, Spain
Madrid, 2007
ISBN: 84-933255-6-2
S.89-91
BioCreative Challenge Evaluation Workshop <2, 2007, Madrid>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer SCAI ()

Abstract
The Gene Mention task is a Named Entity Recognition (NER) task for labeling gene and gene product names in biomedical text. To deal with acceptable alternatives additionally to the gold standard, we use combinations of Conditional Random Fields (CRF) together with a normalizing tagger. This process is followed by a postprocessing step including an acronym disambiguation based on Latent Semantic Analysis (LSA). For robust model selection we apply 50-fold Bootstrapping to obtain an average F-Score of 84.58 % on the trainingset and 86.33 % on the test set.

: http://publica.fraunhofer.de/dokumente/N-57494.html