Open prateekagrawal06 opened 7 years ago
No need to use make_feature_dict for the RNN. Either one-hot encoding or word2vec vectors as input to RNN.
On Apr 21, 2017, at 4:52 PM, prateekagrawal06 notifications@github.com wrote:
Hi Professor,
In part 2 of the assignment.
Do you want us to train RNN on the data we get after vectorizing the make_feature_dict function? Or do you want us to evaluate a totally different approach where we decide what kind of feature we want to go in RNN.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
Hi Prof. @aronwc ,
could you please elaborate more with small example ? it is bit confusing as what should be the input and output ?
Input are words, outputs are NER labels. Each word is a vector, either one hot, like our example in class, or the output of word2vec.
On Apr 22, 2017, at 1:52 AM, schanged notifications@github.com wrote:
Hi Prof. @aronwc ,
could you please elaborate more with small example ? it is bit confusing as what should be the input and output ?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.
Hi Professor,
In part 2 of the assignment.
Do you want us to train RNN on the data we get after vectorizing the make_feature_dict function? Or do you want us to evaluate a totally different approach where we decide what kind of feature we want to go in RNN.