Clinical Records of Traditional Chinese Medicine using Conditional Random Fields and Reasonable Features

A preliminary work on symptom name recog-nition from free-text clinical records (FCRs) of traditional Chinese medicine (TCM) is de-picted in this paper. This problem is viewed as labeling each character in FCRs of TCM with a pre-defined tag (“B-SYC”, “I-SYC ” or “O-SYC”) to indicate the character’s role (a be-ginning, inside or outside part of a symptom name). The task is handled by Conditional Random Fields (CRFs) based on two types of features. The symptom name recognition F-Measure can reach up to 62.829 % with recog-nition rate 93.403 % and recognition error rate 52.665 % under our experiment settings. The feasibility and effectiveness of the methods and reasonable features are verified, and sev-eral interesting and helpful results are shown. A detailed analysis for recognizing symptom names from FCRs of TCM is presented through analyzing labeling results of CRFs. 1 Introduction* Traditional Chinese medicine (TCM), a comple-mentary medical theory to western medicine, pro-vides a distinct way to view our human life (Pal