rguthrie3 / bilstm-crf Goto Github PK

From https://github.com/rguthrie3/BiLSTM-CRF/blob/master/model.py#L114 it appears that transition[j][i] is the score for transitioning from tag i to tag j. However in https://github.com/rguthrie3/BiLSTM-CRF/blob/master/model.py#L52 the comment says the opposite. I guess it doesn't matter because the updates are still consistent, but should the comment change maybe?

Hello!
thank you for sharing the code

can you please give me more explanation how to get Matrix that maps from Bi-LSTM output to num tags and Transition matrix for tagging layer

self.lstm_to_tags_params = self.model.add_parameters((tagset_size, hidden_dim))
self.transitions = self.model.add_lookup_parameters((tagset_size, tagset_size))

Hey,

Just saw that you ported this as a tutorial for PyTorch http://pytorch.org/tutorials/beginner/nlp/advanced_tutorial.html#implementation-notes, and it looks great!

Now I'm curious about the snippet

"The implementation is not optimized. If you understand what is going on, you’ll probably quickly see that iterating over the next tag in the forward algorithm could probably be done in one big operation. I wanted to code to be more readable. If you want to make the relevant change, you could probably use this tagger for real tasks."

Seems like this implementation is the same, did you ever find a way to optimize it? Would save me the trouble, since I'm still very new to PyTorch (unfortunately, static models don't cut it for my use case at the moment …)