multi-class-text-classification-cnn-rnn
multi-class-text-classification-cnn-rnn copied to clipboard
How to change parametrs to much bigger text on russian?
Thanks for your code it's pretty much exactly what i was looking for. But i need to classify bigger text (around 500 words in one article), and it's gonna be in Russian language. Can you advise how to improve code for this?
What do i need to change in config file? batch_size": 256, "dropout_keep_prob": 0.5, "embedding_dim": 300, "evaluate_every": 100, "filter_sizes": "3,4,5", "hidden_unit": 300, "l2_reg_lambda": 0.0, "max_pool_size": 4, "non_static": false, "num_epochs": 1, "num_filters": 128
What do i need to change for bigger sentences?
You will be able to adjust the training parameters once you understand what are they. http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/
Thx for the link!