NLP Classification

nlp_classification.py

import tensorflow_datasets as tfds
import tensorflow as tf

dataset, info = tfds.load('imdb_reviews', with_info=True,
                          as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']

def experiment(train, test):
    VOCAB_SIZE = 1000
    encoder = tf.keras.layers.experimental.preprocessing.TextVectorization(max_tokens=VOCAB_SIZE, standardize=None)
    encoder.adapt(train_dataset.map(lambda text, label: text))
    model = tf.keras.Sequential([
        encoder,
        tf.keras.layers.Embedding(
            input_dim=len(encoder.get_vocabulary()),
            output_dim=64,
            # Use masking to handle the variable sequence lengths
            mask_zero=True),
        tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
        tf.keras.layers.Dense(64, activation='relu'),
        tf.keras.layers.Dense(1)
    ])
    model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              optimizer=tf.keras.optimizers.Adam(1e-4),
              metrics=['accuracy'])
    history = model.fit(train, epochs=20,
                    validation_data=test,
                    validation_steps=30)