Skip to main content

Table 2 Performance of SSVMs and CRFs based NER systems when different features and tag representations were used.

From: Recognizing clinical entities in hospital discharge summaries using Structural Support Vector Machines with word representation features

Tags

Features

SSVMs - F(R/P)(%)

CRFs - F(R/P)(%)

BIO

Base

84.89(83.39/86.44)

84.62 (82.35/87.01)

 

Base + Clustering

85.22(84.05/86.43)

85.16 (82.94/87.50)

 

Base + Distributional

85.19(84.00/86.42)

85.12(82.80/87.58)

 

Base + Clustering + Distributional

85.45(84.30/86.63)

85.31(83.19/87.54)

BIESO

Base

85.42(83.60/87.31)

85.04(82.31/87.97)

 

Base + Clustering

85.74(84.15/87.40)

85.59(83.16/88.16)

 

Base + Distributional

85.74(84.16/87.38)

85.35(82.82/88.05)

 

Base + Clustering + Distributional

85.82(84.31/87.38)

85.68(83.30/88.20)