Skip to Main Content
Table 11: 

Analysis of predicted supertag structures in the redistributed evaluation set. Incorrect predictions are broken down in terms of having the correct structure (✓ struct: the same number and arrangement of slashes, arguments, and results as the gold category), an incorrect but well-formed structure (✓ formed: diverging arrangement of arguments, but still obeying the grammar in Figure 2), or an invalid structure (✗ formed, e.g., missing arguments to slashes).

ModelCorrectIncorrect
✓struct✓formed✗formed
All MLP_10@ 47,542 1,345 4,746 – 
MLP_1@ 47,552 1,401 4,811 – 
K+19 43,120 2,706 7,812 127 
RNN@ 47,704 1,395 4,661 
TreeRNN@ 47,733 1,373 4,659 
AddrMLP@ 47,851 1,352 4,562 
 
Invented K+19 201 96 160 127 
RNN@ 93 26 71 
TreeRNN@ 162 83 213 
AddrMLP@ 190 89 240 
ModelCorrectIncorrect
✓struct✓formed✗formed
All MLP_10@ 47,542 1,345 4,746 – 
MLP_1@ 47,552 1,401 4,811 – 
K+19 43,120 2,706 7,812 127 
RNN@ 47,704 1,395 4,661 
TreeRNN@ 47,733 1,373 4,659 
AddrMLP@ 47,851 1,352 4,562 
 
Invented K+19 201 96 160 127 
RNN@ 93 26 71 
TreeRNN@ 162 83 213 
AddrMLP@ 190 89 240 
Close Modal

or Create an Account

Close Modal
Close Modal