Skip to Main Content
Table 14 

Results for our three models trained on the EfCamDat data set and tested on Toefl11, using continuous classifier outputs. Best result per column in bold, best result per row grouping is underlined.

 FeatureAccuracy (%)
Baselines Random Baseline 11.1 
Majority Class Baseline 11.1 
Single Vector Baseline 32.3 
Current Best (Malmasi and Dras 2015) 33.5 
  
Oracles Accuracy@2 49.9 
Accuracy@3 59.2 
Oracle 64.9 
  
Ensembles Plurality Voting 32.7 
Borda Count 32.6 
Mean Probability 33.5 
Median Probability 33.0 
  
Meta-classifier Linear SVM 42.7 
Logistic Regression 42.7 
Ridge Regression 42.0 
LDA 43.3 
  
Meta-classifier Linear SVM 43.1 
Bagging Logistic Regression 43.0 
Ridge Regression 42.6 
LDA 43.7 
 FeatureAccuracy (%)
Baselines Random Baseline 11.1 
Majority Class Baseline 11.1 
Single Vector Baseline 32.3 
Current Best (Malmasi and Dras 2015) 33.5 
  
Oracles Accuracy@2 49.9 
Accuracy@3 59.2 
Oracle 64.9 
  
Ensembles Plurality Voting 32.7 
Borda Count 32.6 
Mean Probability 33.5 
Median Probability 33.0 
  
Meta-classifier Linear SVM 42.7 
Logistic Regression 42.7 
Ridge Regression 42.0 
LDA 43.3 
  
Meta-classifier Linear SVM 43.1 
Bagging Logistic Regression 43.0 
Ridge Regression 42.6 
LDA 43.7 
Close Modal

or Create an Account

Close Modal
Close Modal