Thanks for you paper and code. But I'm confused with some code.

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Some question about the code and training time. about cws HOT 3 OPEN

jcyk commented on July 3, 2024

Some question about the code and training time.

from cws.

Comments (3)

sevenights commented on July 3, 2024

I don't know if I have expressed it clearly. And my chinese is much better than English :D

from cws.

jcyk commented on July 3, 2024

@sevenights
Hi,

I treat Theano as a legacy in deep learning and am not familiar with it anymore.

I would refer you to a better implementation there. It is with a modern library, i.e. dynet.

from cws.

sevenights commented on July 3, 2024

But in the greedyCWS, there is no need to calculate the update gate for word representation. In the paper

an update gate z (As in Figure 2), which has been shown helpless to the performance but requires uge computational cost according toour empirical study.

So I read the dy_model.py and get the same question.

update_gate = dy.transpose(dy.concatenate_cols([dy.softmax(dy.pickrange(update_logits,i*(wlen+1),(i+1)*(wlen+1))) for i in xrange(self.options['ndims'])]))

which I thought to be:

update_gate = dy.concatenate_cols([dy.softmax(dy.pickrange(update_logits,i*(self.options['ndims']+1),(i+1)*(self.options['ndims']+1))) for i in xrange(wlen)])

from cws.

Recommend Projects