实战是学习一门技术最好的方式，也是深入了解一门技术唯一的方式。因此，NLP专栏计划推出一个实战专栏，让有兴趣的同学在看文章之余也可以自己动手试一试。
本篇介绍自然语言处理中最基础的词向量的训练。
作者&编辑 | 小Dream哥
1 语料准备
用于词向量训练的语料应该是已经分好词的语料，如下所示：
2 词向量训练
(1) 读取语料数据
读取数据的过程很简单，就是从压缩文件中读取上面显示的语料，得到一个列表。
def read_data(filename): with zipfile.ZipFile(filename) as f: data = tf.compat.as_str(f.read(f.namelist()[0])).split() return data
(2) 根据语料，构建字典
构建字典几乎是所有NLP任务所必须的步骤。
def build_dataset(words): 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 data=[dictionary[word] if word in dictionary else 0 for word in words] count[0][1] = unk_count reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys())) return data, count, dictionary, reverse_dictionary
(3) 根据语料，获取一个batch的数据
这里需要解释一下，此次词向量的训练，采用的是skip gram的方式，即通过一个词，预测该词附近的词。generate_batch函数中，skip_window表示取该词左边或右边多少个词，num_skips表示总共取多少个词。最后生成的batch数据，batch是num_skips*batch_size个词，label是中间的batch_size个词。
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) for i in range(batch_size // num_skips): target = skip_window 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) return batch, labels
(4) 用tensforslow训练词向量
首先，构造tensorflow运算图，主要包括以下几个步骤：
1.用palceholder先给训练数据占坑；
2.初始化词向量表，是一个|V|*embedding_size的矩阵，目标就是优化这个矩阵；
3.初始化权重；
4.构建损失函数，这里用NCE构建；
5.构建优化器；
6.构建变量初始化器
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) # operations and variables # 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]))
ncs_loss_test=tf.nn.nce_loss(weights=nce_weights, biases=nce_biases,labels=train_labels, inputs=embed, num_sampled=num_sampled, num_classes=vocabulary_size)
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.initialize_all_variables()
然后，开始训练词向量：
num_steps = 1000 with tf.Session(graph=graph) as session: # we must initialize all variables before using them init.run() print('initialized.') # loop through all training steps and keep track of loss average_loss = 0 for step in range(num_steps): # generate a minibatch of training data batch_inputs, batch_labels = generate_batch(batch_size, num_skips, skip_window) feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels} # we perform a single update step by evaluating the optimizer operation (including it # in the list of returned values of session.run()) _, loss_val,ncs_loss_ = session.run([optimizer, loss,ncs_loss_test], feed_dict=feed_dict) average_loss = loss_val final_embeddings = normalized_embeddings.eval() print(final_embeddings)
(5) 保存词向量
将训练好的词向量写到文件中备用。
final_embeddings = normalized_embeddings.eval() print(final_embeddings) fp=open('vector.txt','w',encoding='utf8') for k,v in reverse_dictionary.items(): t=tuple(final_embeddings[k]) s='' for i in t: i=str(i) s =i " " fp.write(v " " s "n") fp.close()
最后，我们将词向量写到了vector.txt里面，得到了一份很大的词向量表，我们看看它长成什么样子：
可以看到，词向量就是将每个中文词用一个向量来表示，整个词表及其词向量构成了这份词向量表。
这里留一个作业，读者可以自己试一下，从表中读取出来几个词的向量，计算出来他们的相似度，看训练出来的词向量质量如何。
至此本文介绍了如何利用tensorflow平台自己写代码，训练一份自己想要的词向量，代码在我们有三AI的github可以
https://github.com/longpeng2008/yousan.ai/tree/master/natural_language_processing
找到word2vec文件夹，执行python3 w2v_skip_gram.py就可以运行，训练词向量了。
总结
这里讲述了词向量的具体训练过程，相关的原理在我之前的系列文章里有详细的讲述，感兴趣的同学可以好好看一下：
【NLP-词向量】词向量的由来及本质
【NLP-词向量】从模型结构到损失函数详解word2vec
词向量是NLP开始迈进“现代化”的关键，是各种面试必问的基础，需重视。
