Skip to main content

Advertisement

Table 7 Accuracy results for tag attributes

From: An annotation and modeling schema for prescription regimens

Choice Attributes Baseline Literal Fallback Levenshtein Fallback Classifier
form 0.597 0.944 0.965 0.944
route 0.339 0.667 0.738 0.887
side 0.792 0.935 0.173 0.935
unit 0.477 0.831 0.869 0.823
Attributes of FREQ Baseline Hybrid Classifier  
every 0.808 0.984 0.981  
to_every 0.954 1.000 0.986  
times_per 0.570 0.927 0.900  
to_times_per 0.876 0.949 0.954  
unit 0.722 0.976 0.976  
Attributes of TIMING Baseline Hybrid Classifier  
direction 0.396 0.990 0.990  
event 0.406 0.919 0.919  
offset 0.480 0.883 0.742  
to_offset 0.866 0.950 0.950  
offset_unit 0.430 0.826 0.826  
Numeric Attributes Un-normalized Normalized   
amt 0.160 0.927   
to_amt 0.882 0.857   
num 0.115 0.885   
to_num 0.836 0.885   
quantity 0.889 1.000   
to_quantity 1.000 1.000   
Boolean Attributes Baseline Classifier   
refill 0.333 1.000   
subst 0.500 0.615