|
|
|
|
|
|
by wodenokoto
3692 days ago
|
|
|
One hot vectors. You build a dictionary of all words + one catch all for unknown words. Each word then has a position in a sparse vector. So for example : Yes = (0,0,1,0,0,...)
No = (0,0,0,1,0,....) Convolutional and recurrent nets can handle inputs of arbitrary lengths. |
|
|