-
Hi,
according to Table 1 of your paper, "No models use character embeddings or lexicons. " The character embeddings is very useful for sequence labeling as stated by (G Lample - 2016) and (X Ma - …
egrcc updated
6 years ago
-
Hi, @nreimers
when I run the Train_NER_German.py, I got the following error. Please have a look at the issue. Thanks.
`Using Theano backend.
Using gpu device 1: GeForce GTX TITAN X (CNMeM is …
-
Hi @reckart I am new to python so i need your help.... I tried to train the model using English dataset and Glove3 (glove.840B.300d) word embeddings by running Train_NER_German.py. Since the original…
-
python Train_NER_German.py
Using TensorFlow backend.
Generate new embeddings files for a dataset: pkl/GermEval_2014_tudarmstadt_german_50mincount.vocab.pkl
Read file: 2014_tudarmstadt_german_50min…
-
```
if self.use_shape:
shape_embeddings_shape = (self.shape_domain_size - 1, self.shape_size)
w_s = tf_utils.initialize_embeddings(shape_embeddings_shape…
-
-
I am building a CNN+RNN model for speech recognition. But it seems a lot problems with MXNet's rnn API?
I followed the rnn example and trained my network finally after someone's help.
But when it come…
-
I got this issue and have no idea to resolve. I need your help.
-
The example under [Additional Feature Support](https://github.com/aonotas/deep-crf#additional-feature-support) in the readme, mentions arguments −−input idx and −−output idx, that are not handled yet.…
-
Hello,
First of all, thank you very much for making your work open-source to the public!
I am trying to reuse the code to apply it for Twitter NER as described in this [paper](http://noisy-text.…