如何使用卷积神经网络 (python) 构建深度学习文本分类器

Question

What are the steps I would need to take to build a deep learning text classifier, more specifically a text classifier that identifies an author (authorship attribution) in a set of unlabeled texts? The model I am looking at using is word-word CNN (convolutional neural network) which has proven to be very successful in things such as text classification. I am looking to build this model in python.

I am new to deep learning so any resources and information is appreciated.

Answer 1

An End to End Example to demonstrate how to use Convolutional Neural Networks for Text Classification using Tensorflow.Keras is shown below:

from tensorflow.keras.models import Sequential
from tensorflow.keras import layers
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing import sequence
max_features = 10000
max_len = 500
print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=max_len)
x_test = sequence.pad_sequences(x_test, maxlen=max_len)
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

model = Sequential()
model.add(layers.Embedding(max_features, 128, input_length=max_len))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.MaxPooling1D(5))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.GlobalMaxPooling1D())
model.add(layers.Dense(1))
model.summary()
model.compile(optimizer=RMSprop(lr=1e-4),
loss='binary_crossentropy',
metrics=['acc'])
history = model.fit(x_train,y_train,epochs=10,batch_size=128,validation_split=0.2)

For more information please refer Section 6.4 Sequence processing with convnets in the book, Deep Learning Using Python written by Francois Chollet, the Father of Keras.

Hope this helps. Happy Learning!