TreeLSTMSentiment

TreeLSTMSentiment copied to clipboard

ClassNotFoundException when producing dependency parsers

1

When I tried to run the cmd in the 'dependency_parse' function in preprocess_sst.py, an error occurred as follows: `Caused by: java.lang.ClassNotFoundException: edu.stanford.nlp.tagger.maxent.ExtractorNonAlphanumeric` I guess ExtractorNonAlphanumeric should exist in the corresponding...

Lucho0491

the binaryTree implementation (https://github.com/ttpro1995/TreeLSTMSentiment/blob/c61f73e3efdf227e2cb521157f320ec727f2490a/model.py#L111) does not work for constituency trees with only left child and no right child.

sopankhosla

What is getParameters() used for?

2

Looks like nowhere is that called.

ZhaofengWu

Doubts about the BInaryTreeLSTM implementation

7

In your implementation of the BinaryTreeLSTM, 1. Can you explain the leaf / base condition - self.ox just passes through a linear layer, that is understandable since there is no...

ksolaiman

Problem with Binary classification

2

If we make the fine_grain False, it performs the binary classification. But with binary, I can see there are three labels 0, 1, 2. So is it really a binary...

navid5792

bug in testing for fine-grain classification

1

https://github.com/ttpro1995/TreeLSTMSentiment/blob/c61f73e3efdf227e2cb521157f320ec727f2490a/trainer.py#L73 We need to do this only for binary classification. But for fine-grained it should be removed.

gv22ga