Table 4: 
Ablation study for modules used in the encoder and decoder of the CGE model.
ModelBLEUCHRF++#P
CGE 17.38 45.68 61.5 
 
Global Encoder 
-Global Attention 15.59 43.71 59.0 
-FFN 16.33 44.86 50.4 
-Global Encoder 15.17 43.30 45.6 
 
Local Encoder 
-Local Attention 16.92 45.97 61.5 
-Weight Relations 16.88 45.61 53.6 
-GRU 16.38 44.71 60.2 
-Local Encoder 14.68 42.98 51.8 
 
-Shared Vocab. 16.92 46.16 81.8 
 
Decoder 
–Length Penalty 16.68 44.68 61.5 
ModelBLEUCHRF++#P
CGE 17.38 45.68 61.5 
 
Global Encoder 
-Global Attention 15.59 43.71 59.0 
-FFN 16.33 44.86 50.4 
-Global Encoder 15.17 43.30 45.6 
 
Local Encoder 
-Local Attention 16.92 45.97 61.5 
-Weight Relations 16.88 45.61 53.6 
-GRU 16.38 44.71 60.2 
-Local Encoder 14.68 42.98 51.8 
 
-Shared Vocab. 16.92 46.16 81.8 
 
Decoder 
–Length Penalty 16.68 44.68 61.5 
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. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept