And now I go back to NIPS reviewing. Ugh...
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 …
-
-
-
I think I see an immediate application of your blog post.
End of conversation
New conversation -
-
-
any reason you chose Glove over word2vec?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Dai & Le https://arxiv.org/abs/1511.01432 claimed state of the art performance was 85% on that problem. Were they off?
-
probably not using the same test set; I use a random 20% of the training data. But 85% seems very low.
- Show replies
New conversation -
-
-
how this data set is close to real data?
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.