【NLP】语言模型和迁移学习

import tensorflow as tf
from keras import backend as K
import keras.layers as layers
from keras.models import Model

# Initialize session
sess = tf.Session()
K.set_session(sess)

# Instantiate the elmo model
elmo_model = hub.Module("https://tfhub.dev/google/elmo/1", trainable=True)
sess.run(tf.global_variables_initializer())
sess.run(tf.tables_initializer())

# We create a function to integrate the tensorflow model with a Keras model
# This requires explicitly casting the tensor to a string, because of a Keras quirk
def ElmoEmbedding(x):
    return elmo_model(tf.squeeze(tf.cast(x, tf.string)), signature="default", as_dict=True)["default"]

input_text = layers.Input(shape=(1,), dtype=tf.string)
embedding = layers.Lambda(ElmoEmbedding, output_shape=(1024,))(input_text)
dense = layers.Dense(256, activation='relu')(embedding)
pred = layers.Dense(1, activation='sigmoid')(dense)

model = Model(inputs=[input_text], outputs=pred)

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()

# location: fastai/lm_rnn.py

def get_language_model(n_tok, emb_sz, n_hid, n_layers, pad_token,
                 dropout=0.4, dropouth=0.3, dropouti=0.5, dropoute=0.1, wdrop=0.5, tie_weights=True, qrnn=False, bias=False):
    """Returns a SequentialRNN model.

    A RNN_Encoder layer is instantiated using the parameters provided.

    This is followed by the creation of a LinearDecoder layer.

    Also by default (i.e. tie_weights = True), the embedding matrix used in the RNN_Encoder
    is used to  instantiate the weights for the LinearDecoder layer.

    The SequentialRNN layer is the native torch's Sequential wrapper that puts the RNN_Encoder and
    LinearDecoder layers sequentially in the model.

    Args:
        n_tok (int): number of unique vocabulary words (or tokens) in the source dataset
        emb_sz (int): the embedding size to use to encode each token
        n_hid (int): number of hidden activation per LSTM layer
        n_layers (int): number of LSTM layers to use in the architecture
        pad_token (int): the int value used for padding text.
        dropouth (float): dropout to apply to the activations going from one LSTM layer to another
        dropouti (float): dropout to apply to the input layer.
        dropoute (float): dropout to apply to the embedding layer.
        wdrop (float): dropout used for a LSTM's internal (or hidden) recurrent weights.
        tie_weights (bool): decide if the weights of the embedding matrix in the RNN encoder should be tied to the
            weights of the LinearDecoder layer.
        qrnn (bool): decide if the model is composed of LSTMS (False) or QRNNs (True).
        bias (bool): decide if the decoder should have a bias layer or not.
    Returns:
        A SequentialRNN model
    """
    rnn_enc = RNN_Encoder(n_tok, emb_sz, n_hid=n_hid, n_layers=n_layers, pad_token=pad_token,
                 dropouth=dropouth, dropouti=dropouti, dropoute=dropoute, wdrop=wdrop, qrnn=qrnn)
    enc = rnn_enc.encoder if tie_weights else None
    return SequentialRNN(rnn_enc, LinearDecoder(n_tok, emb_sz, dropout, tie_encoder=enc, bias=bias))


def get_rnn_classifier(bptt, max_seq, n_class, n_tok, emb_sz, n_hid, n_layers, pad_token, layers, drops, bidir=False,
                      dropouth=0.3, dropouti=0.5, dropoute=0.1, wdrop=0.5, qrnn=False):
    rnn_enc = MultiBatchRNN(bptt, max_seq, n_tok, emb_sz, n_hid, n_layers, pad_token=pad_token, bidir=bidir,
                      dropouth=dropouth, dropouti=dropouti, dropoute=dropoute, wdrop=wdrop, qrnn=qrnn)
    return SequentialRNN(rnn_enc, PoolingLinearClassifier(layers, drops))

# location: finetune-transformer-lm/train.py

def model(X, M, Y, train=False, reuse=False):
    with tf.variable_scope('model', reuse=reuse):
        # n_special=3，作者把数据集分为三份
        # n_ctx 应该是 n_context
        we = tf.get_variable("we", [n_vocab+n_special+n_ctx, n_embd], initializer=tf.random_normal_initializer(stddev=0.02))
        we = dropout(we, embd_pdrop, train)

        X = tf.reshape(X, [-1, n_ctx, 2])
        M = tf.reshape(M, [-1, n_ctx])

        # 1. Embedding
        h = embed(X, we)

        # 2. transformer block
        for layer in range(n_layer):
            h = block(h, 'h%d'%layer, train=train, scale=True)

        # 3. 计算语言模型loss
        lm_h = tf.reshape(h[:, :-1], [-1, n_embd])
        lm_logits = tf.matmul(lm_h, we, transpose_b=True)
        lm_losses = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=lm_logits, labels=tf.reshape(X[:, 1:, 0], [-1]))
        lm_losses = tf.reshape(lm_losses, [shape_list(X)[0], shape_list(X)[1]-1])
        lm_losses = tf.reduce_sum(lm_losses*M[:, 1:], 1)/tf.reduce_sum(M[:, 1:], 1)

        # 4. 计算classifier loss
        clf_h = tf.reshape(h, [-1, n_embd])
        pool_idx = tf.cast(tf.argmax(tf.cast(tf.equal(X[:, :, 0], clf_token), tf.float32), 1), tf.int32)
        clf_h = tf.gather(clf_h, tf.range(shape_list(X)[0], dtype=tf.int32)*n_ctx+pool_idx)

        clf_h = tf.reshape(clf_h, [-1, 2, n_embd])
        if train and clf_pdrop > 0:
            shape = shape_list(clf_h)
            shape[1] = 1
            clf_h = tf.nn.dropout(clf_h, 1-clf_pdrop, shape)
        clf_h = tf.reshape(clf_h, [-1, n_embd])
        clf_logits = clf(clf_h, 1, train=train)
        clf_logits = tf.reshape(clf_logits, [-1, 2])

        clf_losses = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=clf_logits, labels=Y)
        return clf_logits, clf_losses, lm_losses