New blog post: using pre-trained word embeddings in Keras to solve a text classification problem http://blog.keras.io/using-pre-trained-word-embeddings-in-a-keras-model.html …
-
In fact, running your code, I am getting 95% even without pre-trained vecs! (Theano backend)
try it on the official split, I'd be curious to see the results. Btw pretrained vects would at least speed up training.
-
-
Will do. Running into an issue tho: with shorter sequences (e.g, 100 or less), ZeroDivisionsError in initializations.py
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.