keras-language-modeling

keras-language-modeling copied to clipboard

What changes are needed to run the CNN model?

2

Hi, I try changing the attention model to cnn without success. I get complaints about shape of input layers. Can you give me some ideas what to fix in order...

wailoktam

I checked out code from master branch and printed sims shape. in insurance_qa_eval.py, after line 179 (sims = self.model.predict([question, answers]) ), I printed sims shape "print(sims.shape)" nb_epoch is set to...

jdongca2003

In the blog post and in the related literature about attention LSTM, attention is incorporated like `attention_state = tanh(dot(attention_vec, W_attn) + dot(new_hidden_state, U_attn))` However, in attention_lstm.py it is incorporated like:...

ns-moosavi

Hi, I am trying your work on different data sets, such as the WikiQA. So I think I need to retrain word2vec weights and change the line: 'initial_embed_weights': np.load('word2vec_100_dim.embeddings'). But...

wailoktam

Any idea to get the performance to 70%

24

Hi, I mean without doing something not in the paper [dos santos 2016](http://arxiv.org/abs/1602.03609) I am mentioning 70% coz it is what the author of this paper reported on using the...

wailoktam

_pickle.UnpicklingError: the STRING opcode argument must be quoted

1

Thank you for your great works and support. Continue to do testing on "insurance_qa_eval.py", encountered error below: ###### Using Theano backend. WARNING (theano.configdefaults): g++ not detected ! Theano will be...

PengTedShen

Question on top1-precision evaluation formula

1

Hi, I am wondering why you calculate the top 1 precision by check whether the answer assigned the maximum score by the model is the good answer assigned the maximum...

wailoktam

Output shape of the similarity merge layer is still incorrect

1

I use the latest version and check the similarity part of the model, i.e., qa_model = merge([question_output, answer_output], mode=similarity, output_shape=lambda x: x[:-1],name='similarity') When I invoke qa_model.summary(), here is the screen...

guxd

Can you tell me what test1 and test2 of the insurance data set correspond to in the original data?

1

There are four possibilities validation V1 validation V2 test V1 test V2 Or you split any of them? Many thanks.

wailoktam

Implementation of Unsupervised RNN language model + trained embeddings

1

Hi, I can't find the implementation of this model that was added recently to the [results](https://github.com/codekansas/keras-language-modeling/blob/master/results.notes), and that appears to perform much better than the other ones.

mossaab0