Skip to Main Content
Table 20 

Number of compounds that have been split incorrectly with respect to the gold data. We report numbers of how many of these compounds have fewer split points (under-split), too many split points (over-split), or the correct number but wrong split points (wrongly-split). In addition, we show the total number of missed, wrong, and correct splits for these compounds.

Data Setc’tGermaNetDutch
 number of compounds
# incorrect 35,177 13,612 7,258 
% incorrect 22.17 26.63 32.60 
  
under-split 23,773 7,972 5,849 
over-split 7,843 3,578 806 
wrongly-split 3,561 982 603 
  
 number of splits
missed 29,213 12,537 6,612 
wrong 12,703 2,348 1,520 
correct 20,381 5,216 1,743 
Data Setc’tGermaNetDutch
 number of compounds
# incorrect 35,177 13,612 7,258 
% incorrect 22.17 26.63 32.60 
  
under-split 23,773 7,972 5,849 
over-split 7,843 3,578 806 
wrongly-split 3,561 982 603 
  
 number of splits
missed 29,213 12,537 6,612 
wrong 12,703 2,348 1,520 
correct 20,381 5,216 1,743 
Close Modal

or Create an Account

Close Modal
Close Modal