word vectors, visualizing attention

[andreasvc]

How do I obtain the glove vectors in the right format? I downloaded the pretrained vectors from https://nlp.stanford.edu/projects/glove/ but it's not clear how to convert them to the expected format.

I tried running the code without word vectors (is this supposed to work?) but I get an exception:

/home/andreas/src/Structured-Self-Attentive-Sentence-Embedding/train.py in train(epoch_number)
     79         total_pure_loss += loss.data
     80
---> 81         if attention:  # add penalization term
     82             attentionT = torch.transpose(attention, 1, 2).contiguous()
     83             extra_loss = Frobenius(torch.bmm(attention, attentionT) - I[:attention.size(0)])

/home/andreas/.local/lib/python2.7/site-packages/torch/autograd/variable.pyc in __bool__(self)
    121             return False
    122         raise RuntimeError("bool value of Variable objects containing non-empty " +
--> 123                            torch.typename(self.data) + " is ambiguous")
    124
    125     __nonzero__ = __bool__

RuntimeError: bool value of Variable objects containing non-empty torch.FloatTensor is ambiguous

(If I replace this condition with False the code works).

Lastly, how could I obtain the kind of visualizations of attention as in the paper?

[andreasvc]

I figured out that the word vector file is generated by running train.py in the snli example linked.

As for the exception, replacing if attention: with the following seems to work:

if (attention.data != 0).sum() != 0:

[kaushalshetty]

@andreasvc I had done attention visualization as in the paper. Do check out:
https://github.com/kaushalshetty/Structured-Self-Attention