TensorFlow word2vec_basic 代码分析

将字母向量化（即 word embedding）是NLP的基础，在TensorFlow中有一个简单的实现即word2vec（这篇文章主要关注他的基本实现,demo在这个目录下：tensorflow/examples/tutorials/word2vec/word2vec_basic.py）。关于word2vec的介绍非常多理论也一堆一堆的，下面是本文参考的几篇主要的理论文章：

http://www.jeyzhang.com/tensorflow-learning-notes-3.html

https://liusida.github.io/2016/11/14/study-embeddings/

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/word2vec/word2vec_basic.py

本文希望抛开理论，三言两语的把word2vec用人话说清楚。

一些基本概念不在复述，这里主要总结几个结论：

1.word2vec的学习过程目标是把每个单词映射成一个向量。

2.我们希望这些向量能满足一些基本规律，比如如果两个单词的含义是相近的，那么他们对应的向量的余弦相似度尽可能小。

3.在一个上下文环境中如果单词a出现过多次，单词b也出现过多次，那么a和b极有可能是同个类型的或者意思相近的词。

4.在这里上下文主要指一个单词周围的其他单词。

5.word2vec使用的是skip-gram模型，skip-gram模型是从目标词来预测上下文信息。

所以这里word2vec的模型其实很简单，取其中一个词，作为目标词，当输入目标词的时候，那么理论上就可以输出他的上下文信息。但是它的上下文信息很多，一个目标词周围有很多的词，目标词对应其中任何一个词都是合理的输出。所以将目标词与周围的N个词组成N组训练样本，分别作为输入输出进行训练。

举个例子理解起来就很简单了，一个句子： Y X A B C D E X Ｙ，假设将单词左右两边的两个单词以内的词作为当前词的上下文，当将C作为输入（这时A，B，D，E都是他的上下文），那么他的输出是什么呢， 输出可以是A ，B ， D，E中的任何一个，所以（C,E）,（C,B）（C,D）（C,A），都可以作为训练样本，一般随机选其中的几种进行训练，比如我们只选（C,E），这是C是输入，E是输出（也就是label，机器学习，当给数据打了标签就好办了）。

到现在这个模型应该已经非常清晰了，他的输入是一个单词（应该是一个单词word embedding后对应的数字化后的向量），他的输出也是一个单词，不过输出这里的单词表示方式跟输入不太一样，采用的是One-hot Representation，为什么输入使用word embedding的方式而输出使用One-hot Representation的方式，我的理解是word embedding的方式表示一个单词开始时是有参数的，不是真实的结果，没法用来作为输出去优化模型。

所以对于一个总共有5000个单词的词库，进行word embedding，假设词向量是128维的，那么这个模型的输入是一个1x128的向量，输出是一个1x5000的向量。

]

最后我们把代码贴出来看下:

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.## Licensed under the Apache License, Version 2.0 (the "License");# you may not use this file except in compliance with the License.# You may obtain a copy of the License at##     http://www.apache.org/licenses/LICENSE-2.0## Unless required by applicable law or agreed to in writing, software# distributed under the License is distributed on an "AS IS" BASIS,# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.# See the License for the specific language governing permissions and# limitations under the License.# =============================================================================="""Basic word2vec example."""from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport collectionsimport mathimport osimport randomimport zipfileimport numpy as npfrom six.moves import urllibfrom six.moves import xrange  # pylint: disable=redefined-builtinimport tensorflow as tf# 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 filenamefilename = 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 datavocabulary = read_data(filename)print('Data size', len(vocabulary))# Step 2: Build the dictionary and replace rare words with UNK token.vocabulary_size = 50000def build_dataset(words, n_words):  """Process raw inputs into a dataset."""  count = [['UNK', -1]]  count.extend(collections.Counter(words).most_common(n_words - 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  reversed_dictionary = dict(zip(dictionary.values(), dictionary.keys()))  return data, count, dictionary, reversed_dictionarydata, count, dictionary, reverse_dictionary = build_dataset(vocabulary,                                                            vocabulary_size)del vocabulary  # 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)  if data_index + span > len(data):    data_index = 0  buffer.extend(data[data_index:data_index + span])  data_index += span  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]    if data_index == len(data):      buffer[:] = data[:span]      data_index = span    else:      buffer.append(data[data_index])      data_index += 1  # 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, labelsbatch, 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]])# Step 4: Build and train a skip-gram model.batch_size = 128embedding_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 = 100001with tf.Session(graph=graph) 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    # Note that this is expensive (~20% slowdown if computed every 500 steps)    if step % 10000 == 0:      sim = similarity.eval()      for i in xrange(valid_size):        valid_word = reverse_dictionary[valid_examples[i]]        top_k = 8  # number of nearest neighbors        nearest = (-sim[i, :]).argsort()[1:top_k + 1]        log_str = 'Nearest to %s:' % valid_word        for k in xrange(top_k):          close_word = reverse_dictionary[nearest[k]]          log_str = '%s %s,' % (log_str, close_word)        print(log_str)  final_embeddings = normalized_embeddings.eval()# Step 6: Visualize the embeddings.def plot_with_labels(low_dim_embs, labels, filename='tsne.png'):  assert low_dim_embs.shape[0] >= len(labels), 'More labels than embeddings'  plt.figure(figsize=(18, 18))  # in inches  for i, label in enumerate(labels):    x, y = low_dim_embs[i, :]    plt.scatter(x, y)    plt.annotate(label,                 xy=(x, y),                 xytext=(5, 2),                 textcoords='offset points',                 ha='right',                 va='bottom')  plt.savefig(filename)try:  # pylint: disable=g-import-not-at-top  from sklearn.manifold import TSNE  import matplotlib.pyplot as plt  tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)  plot_only = 500  low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])  labels = [reverse_dictionary[i] for i in xrange(plot_only)]  plot_with_labels(low_dim_embs, labels)except ImportError:  print('Please install sklearn, matplotlib, and scipy to show embeddings.')

其他的就不多说，我想重点分析一下generate_batch这个函数。

# Step 3: Function to generate a training batch for the skip-gram model.#从文本总体的第二个单词开始，每个单词依次作为输入，它的输出可以是上下文范围内的单词中的任何一个单词。一般不是取全部而是随机取其中的几组，以增加随机性。#batch_size 就是每次训练用多少数据，skip_window是确定取一个词周边多远的词来训练，num_skips对于一个输入数据，产生多少个标签数据。所以skip_window决定上下文的长度，就是当前词的周围多少个词内的词被视为它的上下文的范围内，然后从这上下文范围内的词中随机取num_skips个与输入组合成num_skips组训练数据def generate_batch(batch_size, num_skips, skip_window):  global data_index  assert batch_size % num_skips == 0  assert num_skips <= 2 * skip_window #保证num_skips不会超过当前输入的的上下文的总个数  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 ]  #这个很重要，最大长度是span，后面如果数据超过这个长度，前面的会被挤掉，这样使得buffer里面永远是data_index周围的span歌数据，  #而buffer的第skip_window个数据永远是当前处理循环里的输入数据  buffer = collections.deque(maxlen=span)   if data_index + span > len(data):    data_index = 0  buffer.extend(data[data_index:data_index + span])  data_index += span  for i in range(batch_size // num_skips):    target = skip_window  # target label at the center of the buffer    targets_to_avoid = [skip_window] #自己肯定要排除掉，不能自己作为自己的上下文    for j in range(num_skips):      while target in targets_to_avoid:        target = random.randint(0, span - 1) #随机取一个，增强随机性，减少训练时进入局部最优解      targets_to_avoid.append(target)      batch[i * num_skips + j] = buffer[skip_window] #这里保存的是训练的输入序列      labels[i * num_skips + j, 0] = buffer[target] #这里保存的是训练时的输出序列，也就是标签    if data_index == len(data): #超长时回到开始      buffer[:] = data[:span]      data_index = span    else:      buffer.append(data[data_index]) #append时会把queue的开始的几个挤掉      data_index += 1  # 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