about STS task about spm_toolkit HOT 3 CLOSED

1. Please check this link:

   SPM_toolkit/DecAtt/util.py

   Line 120 in de9bc34

   def readSTSdata(dir):

2. For different tasks, I set different value for num_class.
3. For STS, we should use nn.KLDivLoss(), since it is a regression task. There is label conversion for STS, which you may spend some time understanding it.
   for line in open(dir + 'sim.txt'): sim = float(line.strip()) ceil = int(math.ceil(sim)) floor = int(math.floor(sim)) tmp = [0, 0, 0, 0, 0, 0] if floor != ceil: tmp[ceil] = sim - floor tmp[floor] = ceil - sim else: tmp[floor] = 1 labels.append(tmp)

from spm_toolkit.

The code in the image is from the model.py file in the PWIM model.I don't understand why in the STS task, the final dimension of the output is [1, 2].

from spm_toolkit.

Ok, I got your point. Actually the PWIM repo is for my NAACL 18 paper, which I tried character embedding for MSRP, URL and PIT. All these tasks have only two classes.
Sorry about the confusing part, you can remove this line and change the num_class accordingly.

from spm_toolkit.