Skip to Main Content
Table 3: 
Accuracies on the MLDoc zero-shot cross-lingual document classification task (test set).
  EN EN→XX 
  de es fr it ja ru zh 
Schwenk and Li (2018) MultiCCA + CNN 92.20 81.20 72.50 72.38 69.38 67.63 60.80 74.73 
 BiLSTM (Europarl) 88.40 71.83 66.65 72.83 60.73 - - - 
 BiLSTM (UN) 88.83 - 69.50 74.52 - - 61.42 71.97 
 
Proposed method 89.93 84.78 77.33 77.95 69.43 60.30 67.78 71.93 
  EN EN→XX 
  de es fr it ja ru zh 
Schwenk and Li (2018) MultiCCA + CNN 92.20 81.20 72.50 72.38 69.38 67.63 60.80 74.73 
 BiLSTM (Europarl) 88.40 71.83 66.65 72.83 60.73 - - - 
 BiLSTM (UN) 88.83 - 69.50 74.52 - - 61.42 71.97 
 
Proposed method 89.93 84.78 77.33 77.95 69.43 60.30 67.78 71.93 
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