Table 6 
Evaluation results of model ablation.
 Ubuntu CorpusDouban Corpus
R2@1R10@1R10@2R10@5MAPMRRP@1R10@1R10@2R10@5
ReplaceM 0.905 0.661 0.799 0.950 0.503 0.541 0.343 0.201 0.364 0.729 
  
SCN with words 0.919 0.704 0.832 0.955 0.518 0.562 0.370 0.228 0.371 0.737 
SCN with segments 0.921 0.715 0.836 0.956 0.521 0.565 0.382 0.232 0.380 0.734 
SCN ReplaceA 0.918 0.716 0.832 0.954 0.522 0.565 0.376 0.220 0.385 0.727 
SCNlast 0.923 0.723 0.842 0.956 0.526 0.571 0.393 0.236 0.387 0.729 
  
SAN with words 0.922 0.713 0.842 0.957 0.523 0.565 0.372 0.232 0.381 0.747 
SAN with segments 0.928 0.729 0.846 0.959 0.532 0.575 0.385 0.234 0.393 0.754 
SAN ReplaceA 0.927 0.728 0.842 0.959 0.532 0.561 0.386 0.225 0.395 0.757 
SANlast 0.930 0.733 0.850 0.961 0.536 0.581 0.393 0.236 0.404 0.761 
 Ubuntu CorpusDouban Corpus
R2@1R10@1R10@2R10@5MAPMRRP@1R10@1R10@2R10@5
ReplaceM 0.905 0.661 0.799 0.950 0.503 0.541 0.343 0.201 0.364 0.729 
  
SCN with words 0.919 0.704 0.832 0.955 0.518 0.562 0.370 0.228 0.371 0.737 
SCN with segments 0.921 0.715 0.836 0.956 0.521 0.565 0.382 0.232 0.380 0.734 
SCN ReplaceA 0.918 0.716 0.832 0.954 0.522 0.565 0.376 0.220 0.385 0.727 
SCNlast 0.923 0.723 0.842 0.956 0.526 0.571 0.393 0.236 0.387 0.729 
  
SAN with words 0.922 0.713 0.842 0.957 0.523 0.565 0.372 0.232 0.381 0.747 
SAN with segments 0.928 0.729 0.846 0.959 0.532 0.575 0.385 0.234 0.393 0.754 
SAN ReplaceA 0.927 0.728 0.842 0.959 0.532 0.561 0.386 0.225 0.395 0.757 
SANlast 0.930 0.733 0.850 0.961 0.536 0.581 0.393 0.236 0.404 0.761 
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