欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

NLP-词向量(Vector Representations of Words)

程序员文章站 2024-01-15 12:46:46
...

Tensorflow官网词向量 解释和实现公式
为何文本信息要是用Word2Vec呢? 是由于文本信息没有像音频和图片那么多的信息包含,因此词才具有特殊性,为了克服离散的词需要大量数据的支撑,因此采用词向量方式。

NLP-词向量(Vector Representations of Words)


实现逻辑

这里我们进行分布的介绍:主要策略为 DataSet–>转化2维数据–>SkipParam和CBOW–>添加数据至图中–>获取图信息–>TensorBorad中查看

当然如果你感兴趣Skipgram模型是如何工作的Skip-gram的原理中查看。

  • 第一步
    首先我们需要加载我们的训练数据集。此实例中定义了一个maybe_download方法,进行查询是否已经下载,未下载则检查文件大小是否对应则开始下载。
url = 'http://mattmahoney.net/dc/'


def maybe_download(filename, expected_bytes):
    """Download a file if not present, and make sure it's the right size."""
    if not os.path.exists(filename):
        filename, _ = urllib.request.urlretrieve(url + filename, filename)
    statinfo = os.stat(filename)
    if statinfo.st_size == expected_bytes:
        print('Found and verified', filename)
    else:
        print(statinfo.st_size)
        raise Exception(
            'Failed to verify ' + filename + '. Can you get to it with a browser?')
    return filename


filename = maybe_download('text8.zip', 31344016)
  • 第二步
    此步进行讲下载后的text8.zip讲文件对象内的内容转化为字符串,并去掉空格转化为list数组。
# Read the data into a list of strings.
def read_data(filename):
    """Extract the first file enclosed in a zip file as a list of words"""
    with zipfile.ZipFile(filename) as f:
        data = tf.compat.as_str(f.read(f.namelist()[0])).split()
    return data


words = read_data(filename)
print('Data size', len(words))
  • 第三部
    此步骤进行构建我们的字典数据,并且使用字符串UNK进行替换稀疏的单词。
# Step 2: Build the dictionary and replace rare words with UNK token.
# 单词大小为50000
vocabulary_size = 50000

# @param words 传入单词数组
# @param vocabulary_size 要拿到的单词大小
def build_dataset(words, vocabulary_size):

    count = [['UNK', -1]]
    # 罗列每个单词出现的次数
    count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
    # 建立一个空的Map对象 用来存放我们的单词的字典
    dictionary = dict()
    for word, _ in count:
        dictionary[word] = len(dictionary)
    data = list()
    unk_count = 0
    for word in words:
        if word in dictionary:
            index = dictionary[word]
        else:
            index = 0  # dictionary['UNK']
            unk_count += 1
        data.append(index)
    count[0][1] = unk_count
    reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
    return data, count, dictionary, reverse_dictionary


data, count, dictionary, reverse_dictionary = build_dataset(words, vocabulary_size)
del words  # Hint to reduce memory.
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

data_index = 0
  • 第四部
    我们开始进行设置的模型,使用了Skip-gram模型。

NLP-词向量(Vector Representations of Words)


if __name__ == "__main__":
    # Step 4: Build and train a skip-gram model.
    batch_size = 128
    embedding_size = 128  # Dimension of the embedding vector.
    skip_window = 1  # How many words to consider left and right.
    num_skips = 2  # How many times to reuse an input to generate a label.

    # We pick a random validation set to sample nearest neighbors. Here we limit the
    # validation samples to the words that have a low numeric ID, which by
    # construction are also the most frequent.
    valid_size = 16  # Random set of words to evaluate similarity on.
    valid_window = 100  # Only pick dev samples in the head of the distribution.
    valid_examples = np.random.choice(valid_window, valid_size, replace=False)
    num_sampled = 64  # Number of negative examples to sample.

    # graph = tf.Graph()
    #
    # with graph.as_default():

    # Input data.
    train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
    train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
    valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

    # Ops and variables pinned to the CPU because of missing GPU implementation
    with tf.device('/cpu:0'):
        # Look up embeddings for inputs.
        embeddings = tf.Variable(
            tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
        embed = tf.nn.embedding_lookup(embeddings, train_inputs)

        # Construct the variables for the NCE loss
        nce_weights = tf.Variable(
            tf.truncated_normal([vocabulary_size, embedding_size],
                                stddev=1.0 / math.sqrt(embedding_size)))
        nce_biases = tf.Variable(tf.zeros([vocabulary_size]))

    # Compute the average NCE loss for the batch.
    # tf.nce_loss automatically draws a new sample of the negative labels each
    # time we evaluate the loss.
    loss = tf.reduce_mean(
        tf.nn.nce_loss(weights=nce_weights,
                       biases=nce_biases,
                       labels=train_labels,
                       inputs=embed,
                       num_sampled=num_sampled,
                       num_classes=vocabulary_size))

    # Construct the SGD optimizer using a learning rate of 1.0.
    optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

    # Compute the cosine similarity between minibatch examples and all embeddings.
    norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
    normalized_embeddings = embeddings / norm
    valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings, valid_dataset)
    similarity = tf.matmul(valid_embeddings, normalized_embeddings, transpose_b=True)

    # Add variable initializer.
    init = tf.global_variables_initializer()

以下为全部代码:


from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import collections
import math
import os
import random
import zipfile

import numpy as np
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector

from pandas import DataFrame

# Step 1: Download the data.
url = 'http://mattmahoney.net/dc/'


def maybe_download(filename, expected_bytes):
    """Download a file if not present, and make sure it's the right size."""
    if not os.path.exists(filename):
        filename, _ = urllib.request.urlretrieve(url + filename, filename)
    statinfo = os.stat(filename)
    if statinfo.st_size == expected_bytes:
        print('Found and verified', filename)
    else:
        print(statinfo.st_size)
        raise Exception(
            'Failed to verify ' + filename + '. Can you get to it with a browser?')
    return filename


filename = maybe_download('text8.zip', 31344016)


# Read the data into a list of strings.
def read_data(filename):
    """Extract the first file enclosed in a zip file as a list of words"""
    with zipfile.ZipFile(filename) as f:
        data = tf.compat.as_str(f.read(f.namelist()[0])).split()
    return data


words = read_data(filename)
print('Data size', len(words))

# Step 2: Build the dictionary and replace rare words with UNK token.
vocabulary_size = 50000


def build_dataset(words, vocabulary_size):
    count = [['UNK', -1]]
    count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
    dictionary = dict()
    for word, _ in count:
        dictionary[word] = len(dictionary)
    data = list()
    unk_count = 0
    for word in words:
        if word in dictionary:
            index = dictionary[word]
        else:
            index = 0  # dictionary['UNK']
            unk_count += 1
        data.append(index)
    count[0][1] = unk_count
    reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
    return data, count, dictionary, reverse_dictionary


data, count, dictionary, reverse_dictionary = build_dataset(words, vocabulary_size)
del words  # Hint to reduce memory.
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

data_index = 0


# Step 3: Function to generate a training batch for the skip-gram model.
def generate_batch(batch_size, num_skips, skip_window):
    global data_index
    assert batch_size % num_skips == 0
    assert num_skips <= 2 * skip_window
    batch = np.ndarray(shape=(batch_size), dtype=np.int32)
    labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
    span = 2 * skip_window + 1  # [ skip_window target skip_window ]
    buffer = collections.deque(maxlen=span)
    for _ in range(span):
        buffer.append(data[data_index])
        data_index = (data_index + 1) % len(data)
    for i in range(batch_size // num_skips):
        target = skip_window  # target label at the center of the buffer
        targets_to_avoid = [skip_window]
        for j in range(num_skips):
            while target in targets_to_avoid:
                target = random.randint(0, span - 1)
            targets_to_avoid.append(target)
            batch[i * num_skips + j] = buffer[skip_window]
            labels[i * num_skips + j, 0] = buffer[target]
        buffer.append(data[data_index])
        data_index = (data_index + 1) % len(data)
    # Backtrack a little bit to avoid skipping words in the end of a batch
    data_index = (data_index + len(data) - span) % len(data)
    return batch, labels


batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)
for i in range(8):
    print(batch[i], reverse_dictionary[batch[i]], '->', labels[i, 0], reverse_dictionary[labels[i, 0]])

if __name__ == "__main__":
    # Step 4: Build and train a skip-gram model.
    batch_size = 128
    embedding_size = 128  # Dimension of the embedding vector.
    skip_window = 1  # How many words to consider left and right.
    num_skips = 2  # How many times to reuse an input to generate a label.

    # We pick a random validation set to sample nearest neighbors. Here we limit the
    # validation samples to the words that have a low numeric ID, which by
    # construction are also the most frequent.
    valid_size = 16  # Random set of words to evaluate similarity on.
    valid_window = 100  # Only pick dev samples in the head of the distribution.
    valid_examples = np.random.choice(valid_window, valid_size, replace=False)
    num_sampled = 64  # Number of negative examples to sample.

    # graph = tf.Graph()
    #
    # with graph.as_default():

    # Input data.
    train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
    train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
    valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

    # Ops and variables pinned to the CPU because of missing GPU implementation
    with tf.device('/cpu:0'):
        # Look up embeddings for inputs.
        embeddings = tf.Variable(
            tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
        embed = tf.nn.embedding_lookup(embeddings, train_inputs)

        # Construct the variables for the NCE loss
        nce_weights = tf.Variable(
            tf.truncated_normal([vocabulary_size, embedding_size],
                                stddev=1.0 / math.sqrt(embedding_size)))
        nce_biases = tf.Variable(tf.zeros([vocabulary_size]))

    # Compute the average NCE loss for the batch.
    # tf.nce_loss automatically draws a new sample of the negative labels each
    # time we evaluate the loss.
    loss = tf.reduce_mean(
        tf.nn.nce_loss(weights=nce_weights,
                       biases=nce_biases,
                       labels=train_labels,
                       inputs=embed,
                       num_sampled=num_sampled,
                       num_classes=vocabulary_size))

    # Construct the SGD optimizer using a learning rate of 1.0.
    optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

    # Compute the cosine similarity between minibatch examples and all embeddings.
    norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
    normalized_embeddings = embeddings / norm
    valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings, valid_dataset)
    similarity = tf.matmul(valid_embeddings, normalized_embeddings, transpose_b=True)

    # Add variable initializer.
    init = tf.global_variables_initializer()

# Step 5: Begin training.
num_steps = 100001
LOG_DIR = 'D:/Project_coding/Tensorflow/Season2/Word2Vec/log/'

with tf.Session() as session:
    # We must initialize all variables before we use them.
    init.run()
    print("Initialized")

    average_loss = 0
    for step in xrange(num_steps):
        batch_inputs, batch_labels = generate_batch(
            batch_size, num_skips, skip_window)
        feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}

        # We perform one update step by evaluating the optimizer op (including it
        # in the list of returned values for session.run()
        _, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
        average_loss += loss_val

        if step % 2000 == 0:
            if step > 0:
                average_loss /= 2000
            # The average loss is an estimate of the loss over the last 2000 batches.
            print("Average loss at step ", step, ": ", average_loss)
            average_loss = 0

    """
    Use TensorBoard to visualize our model. 
    This is not included in the TensorFlow website tutorial.
    """
    words_to_visualize = 3000
    final_embeddings = normalized_embeddings.eval()[:words_to_visualize]
    embedding_var = tf.Variable(final_embeddings)
    session.run(embedding_var.initializer)
    saver = tf.train.Saver([embedding_var])
    saver.save(session, os.path.join(LOG_DIR, "model.ckpt"), 0)

    # Format: tensorflow/contrib/tensorboard/plugins/projector/projector_config.proto
    config = projector.ProjectorConfig()

    # You can add multiple embeddings. Here we add only one.
    embedding = config.embeddings.add()
    embedding.tensor_name = embedding_var.name
    # Link this tensor to its metadata file (e.g. labels).
    embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')

    # Use the same LOG_DIR where you stored your checkpoint.
    summary_writer = tf.summary.FileWriter(LOG_DIR, session.graph)
    # summary_writer.add_graph()

    # The next line writes a projector_config.pbtxt in the LOG_DIR. TensorBoard will
    # read this file during startup.
    projector.visualize_embeddings(summary_writer, config)

    labels = [(reverse_dictionary[i], i) for i in range(words_to_visualize)]
    DataFrame(labels, columns=['word', 'freq_rank']).to_csv('log/metadata.tsv', index=False, sep='\t')

相关标签: word