Table 4 
Results for models with different context utilization strategies. *: statistically significant (p < .05 on the McNemar test).
  Accuracy (Error)Speed
AllSemiotic classSentence
English (Standard): 
 Word feat. init 99.84% (0.16%) 98.30% (1.70%) 98.20% (1.80%) 1.4x 
concat 99.82% (0.18%) 98.42% (1.58%) 97.96% (2.04%) 1.2x 
  
Russian (Standard): 
 Word feat. init 99.62% (0.38%) 97.01% (2.99%) 95.46% (4.54%) 2.0x 
concat 99.66% (0.34%)* 97.32% (2.68%)* 95.80% (4.20%) 1.7x 
  Accuracy (Error)Speed
AllSemiotic classSentence
English (Standard): 
 Word feat. init 99.84% (0.16%) 98.30% (1.70%) 98.20% (1.80%) 1.4x 
concat 99.82% (0.18%) 98.42% (1.58%) 97.96% (2.04%) 1.2x 
  
Russian (Standard): 
 Word feat. init 99.62% (0.38%) 97.01% (2.99%) 95.46% (4.54%) 2.0x 
concat 99.66% (0.34%)* 97.32% (2.68%)* 95.80% (4.20%) 1.7x 
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