Table 11 
Accuracies of the graph merging–based parser on development set without POSTag information. A first-order graph-based parser with a neural scoring model is used for tree parsing. ELMo is used.
  UPURUFUCMLPLRLFLCM
SM Subgraph1 89.74 79.79 84.47 19.80 85.69 76.19 80.66 17.07 
Subgraph2 89.47 81.63 85.37 19.06 85.43 77.94 81.51 15.94 
Subgraph3 90.62 81.50 85.82 20.76 86.60 77.88 82.01 16.28 
  Merged 84.40 91.24 87.69 22.86 80.59 87.12 83.73 18.15 
  
LR Subgraph1 91.13 80.82 85.67 21.10 86.95 77.11 81.73 17.30 
Subgraph2 90.86 82.78 86.63 20.31 86.67 78.97 82.64 16.73 
Subgraph3 91.56 82.38 86.73 21.21 87.49 78.72 82.88 16.79 
  Merged 88.86 88.97 88.92 28.93 84.98 85.08 85.03 22.12 
  UPURUFUCMLPLRLFLCM
SM Subgraph1 89.74 79.79 84.47 19.80 85.69 76.19 80.66 17.07 
Subgraph2 89.47 81.63 85.37 19.06 85.43 77.94 81.51 15.94 
Subgraph3 90.62 81.50 85.82 20.76 86.60 77.88 82.01 16.28 
  Merged 84.40 91.24 87.69 22.86 80.59 87.12 83.73 18.15 
  
LR Subgraph1 91.13 80.82 85.67 21.10 86.95 77.11 81.73 17.30 
Subgraph2 90.86 82.78 86.63 20.31 86.67 78.97 82.64 16.73 
Subgraph3 91.56 82.38 86.73 21.21 87.49 78.72 82.88 16.79 
  Merged 88.86 88.97 88.92 28.93 84.98 85.08 85.03 22.12 
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