1 Hit in 3.0 sec

Clinical Entity Recognition Using Cost-Sensitive Structured Perceptron for NTCIR-10 MedNLP

Shohei Higashiyama, Kazuhiro Seki, Kuniaki Uehara
2013 NTCIR Conference on Evaluation of Information Access Technologies  
This paper reports on our approach to the NTCIR-10 MedNLP task, which aims at identifying personal and medical information in Japanese clinical texts.  ...  We applied a machine learning (ML) algorithm for sequential labeling, specifically, structured perceptron, and defined a cost function for lowering misclassification cost.  ...  Structured Perceptron and Cost-Sensitive Learning For the MedNLP task, we applied structured perceptron [1] , which can be used for structured prediction including sequence labeling.  ... 
dblp:conf/ntcir/HigashiyamaSU13 fatcat:eo4npafx45fmzcnetbrt66x5py