soujanyaporia / aspect-extraction Goto Github PK

Hello

First of all, thank you for your effort. I have a question about the model's evaluation, what is the difference between chunk-based evaluation and partial matching based evaluation? and why there is a huge difference between their results? I am using the F1 measure for the evaluation of my dataset and got very different results.

Also, I want to ask you if there is any paper to cite the window-CNN+maxpool+CRF model?

Thanks,

Traceback (most recent call last):
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2349, in get_attr
c_api.TF_OperationGetAttrValueProto(self._c_op, name, buf)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Operation 'ExtractImagePatches' has no attr named '_XlaCompile'.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 391, in _MaybeCompile
xla_compile = op.get_attr("_XlaCompile")
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2353, in get_attr
raise ValueError(str(e))
ValueError: Operation 'ExtractImagePatches' has no attr named '_XlaCompile'.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 26, in
main()
File "train.py", line 12, in main
model.build()
File "/home/wsy/qa/aspect_extraction-master/model/aspect_model.py", line 409, in build
self.config.clip)
File "/home/wsy/qa/aspect_extraction-master/model/base_model.py", line 54, in add_train_op
grads, vs= zip(*optimizer.compute_gradients(loss))
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 511, in compute_gradients
colocate_gradients_with_ops=colocate_gradients_with_ops)
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 532, in gradients
gate_gradients, aggregation_method, stop_gradients)
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 701, in _GradientsHelper
lambda: grad_fn(op, *out_grads))
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 396, in _MaybeCompile
return grad_fn() # Exit early
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 701, in
lambda: grad_fn(op, *out_grads))
File "/home/wsy/python36_cuda9/lib/python3.6/site-packages/tensorflow/python/ops/array_grad.py", line 749, in _ExtractImagePatchesGrad
rows_out = int(ceil(rows_in / stride_r))
TypeError: unsupported operand type(s) for /: 'NoneType' and 'int'

could you help me？

what to change in the code to support other language like Arabic or Germany.

@soujanyaporia. I don't seem to understand your readme correctly.