Table 11 
Per-semiotic class error counts with and without covering grammars, covering only classes where there is a difference between using and not using the covering grammar.
 EnglishRussian
StandardKaggleStandardKaggle
CARDINAL: 
 Best model 1 49 1 73 
 + CG decoding 0 15 3 36 
DATE: 
 Best model 2 24 0 33 
 + CG decoding 1 4 0 3 
DECIMAL: 
 Best model 0 0 0 1 
 + CG decoding 0 0 0 7 
DIGIT: 
 Best model 0 4 0 0 
 + CG decoding 0 3 0 0 
MEASURE: 
 Best model 2 453 2 38 
 + CG decoding 1 75 3 29 
MONEY: 
 Best model 0 18 0 9 
 + CG decoding 0 4 1 4 
ORDINAL: 
 Best model 1 2 0 4 
 + CG decoding 0 0 0 2 
 EnglishRussian
StandardKaggleStandardKaggle
CARDINAL: 
 Best model 1 49 1 73 
 + CG decoding 0 15 3 36 
DATE: 
 Best model 2 24 0 33 
 + CG decoding 1 4 0 3 
DECIMAL: 
 Best model 0 0 0 1 
 + CG decoding 0 0 0 7 
DIGIT: 
 Best model 0 4 0 0 
 + CG decoding 0 3 0 0 
MEASURE: 
 Best model 2 453 2 38 
 + CG decoding 1 75 3 29 
MONEY: 
 Best model 0 18 0 9 
 + CG decoding 0 4 1 4 
ORDINAL: 
 Best model 1 2 0 4 
 + CG decoding 0 0 0 2 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy.
Accept