One Hot Encoding giving same number for different words in keras

问题

Why I am getting same results for different words?

import keras
keras.__version__
'1.0.0'
import theano 
theano.__version__
'0.8.1'

from keras.preprocessing.text import one_hot
one_hot('START', 43)
[26]
one_hot('children', 43)
[26]

回答1:

unicity non-guaranteed in one hot encoding

see one hot keras documentation

回答2:

From the Keras source code, you can see that the words are hashed modulo the output dimension (43, in your case):

def one_hot(text, n,
        filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
        lower=True,
        split=' '):
    seq = text_to_word_sequence(text,
                            filters=filters,
                            lower=lower,
                            split=split)
    return [(abs(hash(w)) % (n - 1) + 1) for w in seq]

So it is very likely that there will be a collision.

来源：https://stackoverflow.com/questions/36591078/one-hot-encoding-giving-same-number-for-different-words-in-keras