无涯教程-TensorFlow - 单词嵌入-Toy模板网

这篇具有很好参考价值的文章主要介绍了无涯教程-TensorFlow - 单词嵌入。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

Word embedding是从离散对象(如单词)映射到向量和实数的概念，可将离散的输入对象有效地转换为有用的向量。

Word embedding的输入如下所示:

blue: (0.01359, 0.00075997, 0.24608, ..., -0.2524, 1.0048, 0.06259)
blues: (0.01396, 0.11887, -0.48963, ..., 0.033483, -0.10007, 0.1158)
orange: (-0.24776, -0.12359, 0.20986, ..., 0.079717, 0.23865, -0.014213)
oranges: (-0.35609, 0.21854, 0.080944, ..., -0.35413, 0.38511, -0.070976)

Word2vec

Word2vec是用于无监督最常见方法，它以一种方式训练模型，即给定的输入单词通过使用跳跃语法来预测单词的上下文。

TensorFlow提供了多种方法来实现这种模型，从而提高了复杂性和优化级别，并使用了多线程概念和更高级别的抽象。

import os 
import math 
import numpy as np 
import tensorflow as tf 

from tensorflow.contrib.tensorboard.plugins import projector 
batch_size = 64 
embedding_dimension = 5 
negative_samples = 8 
LOG_DIR = "logs/word2vec_intro" 

digit_to_word_map = {
   1: "One", 
   2: "Two", 
   3: "Three", 
   4: "Four", 
   5: "Five", 
   6: "Six", 
   7: "Seven", 
   8: "Eight", 
   9: "Nine"} 
sentences = [] 

# 创建两种句子 - 奇数和偶数序列。
   for i in range(10000): 
   rand_odd_ints = np.random.choice(range(1, 10, 2), 3) 
      sentences.append(" ".join([digit_to_word_map[r] for r in rand_odd_ints])) 
   rand_even_ints = np.random.choice(range(2, 10, 2), 3) 
      sentences.append(" ".join([digit_to_word_map[r] for r in rand_even_ints])) 
   
# 将单词映射到索引
word2index_map = {} 
index = 0 

for sent in sentences: 
   for word in sent.lower().split(): 
   
   if word not in word2index_map: 
      word2index_map[word] = index 
      index += 1 
index2word_map = {index: word for word, index in word2index_map.items()} 

vocabulary_size = len(index2word_map) 

# 生成skip-gram对
skip_gram_pairs = [] 

for sent in sentences: 
   tokenized_sent = sent.lower().split() 
   
   for i in range(1, len(tokenized_sent)-1):        
      word_context_pair = [[word2index_map[tokenized_sent[i-1]], 
         word2index_map[tokenized_sent[i+1]]], word2index_map[tokenized_sent[i]]] 
      
      skip_gram_pairs.append([word_context_pair[1], word_context_pair[0][0]]) 
      skip_gram_pairs.append([word_context_pair[1], word_context_pair[0][1]]) 

def get_skipgram_batch(batch_size): 
   instance_indices = list(range(len(skip_gram_pairs))) 
      np.random.shuffle(instance_indices)
   batch = instance_indices[:batch_size] 
   x = [skip_gram_pairs[i][0] for i in batch] 
   y = [[skip_gram_pairs[i][1]] for i in batch] 
   return x, y 
   
#批处理示例
x_batch, y_batch = get_skipgram_batch(8) 
x_batch 
y_batch 
[index2word_map[word] for word in x_batch] [index2word_map[word[0]] for word in y_batch] 

#输入数据，标签 train_inputs=tf.placeholder(tf.int32, shape=[batch_size])
   train_labels = tf.placeholder(tf.int32, shape = [batch_size, 1]) 

# 嵌入查找表目前仅在 CPU 中实现
   tf.name_scope("embeddings"): 
   embeddings = tf.Variable(    
      tf.random_uniform([vocabulary_size, embedding_dimension], -1.0, 1.0), 
         name = embedding) 
   # 这本质上是一个查找表
   embed = tf.nn.embedding_lookup(embeddings, train_inputs) 
   
# 为 NCE 损失创建变量
nce_weights = tf.Variable(     
   tf.truncated_normal([vocabulary_size, embedding_dimension], stddev = 1.0/
      math.sqrt(embedding_dimension))) 
   
nce_biases = tf.Variable(tf.zeros([vocabulary_size])) 

loss = tf.reduce_mean(     
   tf.nn.nce_loss(weights = nce_weights, biases = nce_biases, inputs = embed, 
   labels = train_labels,num_sampled = negative_samples, 
   num_classes = vocabulary_size)) tf.summary.scalar("NCE_loss", loss) 
   
# 学习率衰减
global_step = tf.Variable(0, trainable = False) 
   learningRate = tf.train.exponential_decay(learning_rate = 0.1, 
   global_step = global_step, decay_steps = 1000, decay_rate = 0.95, staircase = True) 

train_step = tf.train.GradientDescentOptimizer(learningRate).minimize(loss) 
   merged = tf.summary.merge_all() 
with tf.Session() as sess: 
   train_writer = tf.summary.FileWriter(LOG_DIR,    
      graph = tf.get_default_graph()) 
   saver = tf.train.Saver() 
   
   with open(os.path.join(LOG_DIR, metadata.tsv), "w") as metadata: 
      metadata.write(Name	Class
) for k, v in index2word_map.items(): 
      metadata.write(%s	%d
 % (v, k)) 
   
   config = projector.ProjectorConfig() 
   embedding = config.embeddings.add() embedding.tensor_name = embeddings.name 
   
   # 将此张量链接到其元数据文件（例如标签）。
   embedding.metadata_path = os.path.join(LOG_DIR, metadata.tsv) 
      projector.visualize_embeddings(train_writer, config) 
   
   tf.global_variables_initializer().run() 
   
   for step in range(1000): 
      x_batch, y_batch = get_skipgram_batch(batch_size) summary, _ = sess.run(
         [merged, train_step], feed_dict = {train_inputs: x_batch, train_labels: y_batch})
      train_writer.add_summary(summary, step)
      
      if step % 100 == 0:
         saver.save(sess, os.path.join(LOG_DIR, "w2v_model.ckpt"), step)
         loss_value = sess.run(loss, feed_dict = {
            train_inputs: x_batch, train_labels: y_batch})
         print("Loss at %d: %.5f" % (step, loss_value))

   # 在使用之前规范化嵌入
   norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims = True))
   normalized_embeddings = embeddings /
      norm normalized_embeddings_matrix = sess.run(normalized_embeddings)
   
ref_word = normalized_embeddings_matrix[word2index_map["one"]]

cosine_dists = np.dot(normalized_embeddings_matrix, ref_word)
ff = np.argsort(cosine_dists)[::-1][1:10] for f in ff: print(index2word_map[f])
print(cosine_dists[f])

上面的代码生成以下输出-

TensorFlow - 单词嵌入 - 无涯教程网无涯教程网提供Word embedding是从离散对象(如单词)映射到向量和实数的概念，可将离散的输入对象有效...https://www.learnfk.com/tensorflow/tensorflow-word-embedding.html文章来源地址https://www.toymoban.com/news/detail-660026.html

到了这里，关于无涯教程-TensorFlow - 单词嵌入的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！