实现Word2Vec模型(Skip-Gram):TensorFlow版本

版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
本文链接: https://blog.csdn.net/qq_18310041/article/details/97266951

1. 数据预处理

文本分词、替换文本中特殊符号、去除低频词(Counter 计数器,统计字符出现的个数)、单词映射表

# 筛选低频词
words_count = Counter(words)
words = [w for w in words if words_count[w] > 50]
# 构建映射表
vocab = set(words)
vocab_to_int = {w: c for c, w in enumerate(vocab)}
int_to_vocab = {c: w for c, w in enumerate(vocab)}
print("total words: {}".format(len(words)))
print("unique words: {}".format(len(set(words))))
# 对原文本进行vocab到int的转换
int_words = [vocab_to_int[w] for w in words]

2. 训练样本构建

对停用词进行采样,计算每个单词被删除的概率大小如下:

一文详解 Word2vec 之 Skip-Gram 模型(实现篇)

其中,t是一个阈值参数,一般为1e-3至1e-5;f(wi)是单词 wi 在整个数据集中的出现频次;P(wi)是单词被删除的概率。

t = 1e-5 # t值
threshold = 0.9 # 剔除概率阈值

# 统计单词出现频次
int_word_counts = Counter(int_words)
total_count = len(int_words)
# 计算单词频率
word_freqs = {w: c/total_count for w, c in int_word_counts.items()}
# 计算被删除的概率
prob_drop = {w: 1 - np.sqrt(t / word_freqs[w]) for w in int_word_counts}
# 对单词进行采样
train_words = [w for w in int_words if prob_drop[w] < threshold]
print(len(train_words))

构造batch:基于每个input word的上下文构建batch

设置窗口大小为m,在[1,m]之间生成随机数,作为最终的窗口大小。随机数的窗口重新选择步骤,能够让模型更聚焦于当前input word的邻近词。

# 获得input word的上下文单词列表
def get_targets(words, idx, window_size=5):
    # words: 单词列表
    # idx: input word的索引号
    # window_size: 窗口大小
    target_window = np.random.randint(1, window_size + 1)
    # 这里要考虑input word前面单词不够的情况
    start_point = idx - target_window if (idx - target_window) > 0 else 0
    end_point = idx + target_window
    # output words(即窗口中的上下文单词)
    targets = set(words[start_point: idx] + words[idx + 1: end_point + 1])
    return list(targets)

# 构造一个获取batch的生成器
def get_batches(words, batch_size, window_size=5):
    n_batches = len(words) // batch_size

    # 取所有的batches
    words = words[:n_batches * batch_size]

    for idx in range(0, len(words), batch_size):
        x, y = [], []
        batch = words[idx: idx + batch_size]
        for i in range(len(batch)):
            batch_x = batch[i]
            batch_y = get_targets(batch, i, window_size)
            # 由于一个input word会对应多个output word,因此需要长度统一
            x.extend([batch_x] * len(batch_y))
            y.extend(batch_y)
        yield x, y

3. 模型构建

输入层到嵌入层,一般embeding_size设置为50-300之间

train_graph = tf.Graph()
with train_graph.as_default():
    inputs = tf.placeholder(tf.int32, shape=[None], name='inputs')
    labels = tf.placeholder(tf.int32, shape=[None, None], name='labels')

# 嵌入矩阵的矩阵形状为  vocab_size × hidden_units_size
vocab_size = len(int_to_vocab)
embedding_size = 200 # 嵌入维度

with train_graph.as_default():
    # 嵌入层权重矩阵
    embedding = tf.Variable(tf.random_uniform([vocab_size, embedding_size], -1, 1))
    # 实现lookup
    embed = tf.nn.embedding_lookup(embedding, inputs)

嵌入层到输出层,负采样主要是为了解决梯度下降计算速度慢的问题

n_sampled = 100

with train_graph.as_default():
    softmax_w = tf.Variable(tf.truncated_normal([vocab_size, embedding_size], stddev=0.1))
    softmax_b = tf.Variable(tf.zeros(vocab_size))
    
    # 计算negative sampling下的损失
    # tf.nn.sampled_softmax_loss会在softmax层上进行采样计算损失,计算出的loss要比full softmax loss低
    loss = tf.nn.sampled_softmax_loss(softmax_w, softmax_b, labels, embed, n_sampled, vocab_size)
    
    cost = tf.reduce_mean(loss)
    optimizer = tf.train.AdamOptimizer().minimize(cost)

4. 模型验证

查看训练出的相近语义的词

with train_graph.as_default():
    # 随机挑选一些单词
    ## From Thushan Ganegedara's implementation
    valid_size = 7 # Random set of words to evaluate similarity on.
    valid_window = 100
    # pick 8 samples from (0,100) and (1000,1100) each ranges. lower id implies more frequent 
    valid_examples = np.array(random.sample(range(valid_window), valid_size//2))
    valid_examples = np.append(valid_examples, 
                               random.sample(range(1000,1000+valid_window), valid_size//2))
    valid_examples = [vocab_to_int['word'], 
                      vocab_to_int['ppt'], 
                      vocab_to_int['熟悉'],
                      vocab_to_int['java'], 
                      vocab_to_int['能力'], 
                      vocab_to_int['逻辑思维'],
                      vocab_to_int['了解']]
    
    valid_size = len(valid_examples)
    # 验证单词集
    valid_dataset = tf.constant(valid_examples, dtype=tf.int32)
    
    # 计算每个词向量的模并进行单位化
    norm = tf.sqrt(tf.reduce_sum(tf.square(embedding), 1, keep_dims=True))
    normalized_embedding = embedding / norm
    # 查找验证单词的词向量
    valid_embedding = tf.nn.embedding_lookup(normalized_embedding, valid_dataset)
    # 计算余弦相似度
    similarity = tf.matmul(valid_embedding, tf.transpose(normalized_embedding))

epochs = 10 # 迭代轮数
batch_size = 1000 # batch大小
window_size = 10 # 窗口大小

with train_graph.as_default():
    saver = tf.train.Saver() # 文件存储

with tf.Session(graph=train_graph) as sess:
    iteration = 1
    loss = 0
    sess.run(tf.global_variables_initializer())

    for e in range(1, epochs+1):
        batches = get_batches(train_words, batch_size, window_size)
        start = time.time()
        # 
        for x, y in batches:
            
            feed = {inputs: x,
                    labels: np.array(y)[:, None]}
            train_loss, _ = sess.run([cost, optimizer], feed_dict=feed)
            
            loss += train_loss
            
            if iteration % 100 == 0: 
                end = time.time()
                print("Epoch {}/{}".format(e, epochs),
                      "Iteration: {}".format(iteration),
                      "Avg. Training loss: {:.4f}".format(loss/100),
                      "{:.4f} sec/batch".format((end-start)/100))
                loss = 0
                start = time.time()
            
            # 计算相似的词
            if iteration % 1000 == 0:
                # 计算similarity
                sim = similarity.eval()
                for i in range(valid_size):
                    valid_word = int_to_vocab[valid_examples[i]]
                    top_k = 8 # 取最相似单词的前8个
                    nearest = (-sim[i, :]).argsort()[1:top_k+1]
                    log = 'Nearest to [%s]:' % valid_word
                    for k in range(top_k):
                        close_word = int_to_vocab[nearest[k]]
                        log = '%s %s,' % (log, close_word)
                    print(log)
            
            iteration += 1
            
    save_path = saver.save(sess, "checkpoints/text8.ckpt")
    embed_mat = sess.run(normalized_embedding)

sklearn中的TSNE来对高维词向量进行可视化

5. 提升效果的技巧

  • 增大训练样本,语料库越大,模型学习的可学习的信息会越多。

  • 增加window size,可以获得更多的上下文信息。

  • 增加embedding size可以减少信息的维度损失,但也不宜过大,我一般常用的规模为50-300。

 

参考:https://zhuanlan.zhihu.com/p/27296712

C语言源代码:https://github.com/chrisjmccormick/word2vec_commented

英文教程:http://mccormickml.com/2016/04/27/word2vec-resources/

 

 

猜你喜欢

转载自blog.csdn.net/qq_18310041/article/details/97266951