Clinical Entity Recognition Using Cost-Sensitive Structured Perceptron for NTCIR-10 MedNLP.
Shohei Higashiyama, Kazuhiro Seki, Kuniaki Uehara · NTCIR · 2013
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. On the test set provided by the organizers, our approach achieved an F-score of 77.00 for the de-identification task and 79.14 for the complaint and diagnosis task.