search

cbaziotis / datastories-semeval2017-task4

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
MIT License
196 stars 63 forks source link

2 "Quick-start" questions #34

Closed HyperColumn closed 6 years ago

HyperColumn commented 6 years ago

What is the recommended version of tensorflow/theano to work with? Will un-commenting the line that uses Attention-RNN model and use it instead of cnn-multi-filters should work out-of-the box (model_message.py)?

cbaziotis commented 6 years ago

I just update the codebase in order to be compatible with the latest versions of keras and tensorflow. https://github.com/cbaziotis/datastories-semeval2017-task4/blob/master/requirements.txt

As with your second question, you are correct. I uncommented the right block and tested the code myself. It should work just fine. https://github.com/cbaziotis/datastories-semeval2017-task4/blob/master/models/nn_task_message.py#L80

HyperColumn commented 6 years ago

Thank you for your answer and the updates.