Skip to Main Content
Table 5 

Accuracy rates on the raw text documents of the TOEFL11 corpus (English L2) of various classification systems based on string kernels. The best accuracy rates on each set of experiments are highlighted in bold. The weights a1 and a2 from the weighted sums of kernels are computed by kernel alignment.

MethodDev10-fold CVTest
KRR and  86.3% 82.6% 82.8% 
KRR and  84.5% 82.5% 82.6% 
KRR and  79.9% 77.9% 77.6% 
KRR and  86.1% 82.6% 83.1% 
KRR and  84.9% 82.4% 82.1% 
KRR and  85.6% 82.9% 82.6% 
KRR and  85.6% 82.9% 82.6% 
 
KDA and  86.2% 83.7% 84.6% 
KDA and  85.2% 83.6% 84.3% 
KDA and  81.2% 79.1% 79.6% 
KDA and  86.6% 83.9% 84.7% 
KDA and  85.9% 83.5% 83.9% 
KDA and  85.9% 84.185.1% 
KDA and  86.1% 84.185.3
KDA and  86.784.0% 84.9% 
MethodDev10-fold CVTest
KRR and  86.3% 82.6% 82.8% 
KRR and  84.5% 82.5% 82.6% 
KRR and  79.9% 77.9% 77.6% 
KRR and  86.1% 82.6% 83.1% 
KRR and  84.9% 82.4% 82.1% 
KRR and  85.6% 82.9% 82.6% 
KRR and  85.6% 82.9% 82.6% 
 
KDA and  86.2% 83.7% 84.6% 
KDA and  85.2% 83.6% 84.3% 
KDA and  81.2% 79.1% 79.6% 
KDA and  86.6% 83.9% 84.7% 
KDA and  85.9% 83.5% 83.9% 
KDA and  85.9% 84.185.1% 
KDA and  86.1% 84.185.3
KDA and  86.784.0% 84.9% 
Close Modal

or Create an Account

Close Modal
Close Modal