使用Word Embedding+Keras进行自然语言处理NLP

目录

 介绍：

one-hot： 

 pad_sequences:

 建模:

 介绍：

one-hot： 

### sentences
sentences=[  'the glass of milk',
     'the glass of juice',
     'the cup of tea',
    'I am a good boy',
     'I am a good developer',
     'understand the meaning of words',
     'your videos are good',]

### Vocabulary size
voc_size=10000

onehot_repr=[one_hot(words,voc_size) for words in sentences] 
print(onehot_repr)

'''结果：
[[1607, 1898, 6281, 9401], [1607, 1898, 6281, 3401], [1607, 6359, 6281, 2217], [7508, 378, 2733, 8693, 7438], [7508, 378, 2733, 8693, 5363], [8292, 1607, 4448, 6281, 8555], [1825, 3648, 3717, 8693]]'''

 pad_sequences:

from tensorflow.keras.layers import Embedding
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential

import numpy as np

sent_length=8
embedded_docs=pad_sequences(onehot_repr,padding='pre',maxlen=sent_length)
print(embedded_docs)
 
'''结果：
[[   0    0    0    0 1607 1898 6281 9401]
 [   0    0    0    0 1607 1898 6281 3401]
 [   0    0    0    0 1607 6359 6281 2217]
 [   0    0    0 7508  378 2733 8693 7438]
 [   0    0    0 7508  378 2733 8693 5363]
 [   0    0    0 8292 1607 4448 6281 8555]
 [   0    0    0    0 1825 3648 3717 8693]]
'''

 建模:

dim=10

model=Sequential()
model.add(Embedding(voc_size,dim,input_length=sent_length))
model.compile('adam','mse')

model.summary()