Distributed Representations of Words and Phrases and their Compositionality论文阅读及实战

‘‘‘
  code by Tae Hwan Jung(Jeff Jung) @graykode
‘‘‘
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import matplotlib.pyplot as plt
%matplotlib inline

dtype = torch.FloatTensor  # 定义一个多维张量torch

# 3 Words Sentence
sentences = [ "i like dog", "i like cat", "i like animal",
              "dog cat animal", "apple cat dog like", "dog fish milk like",
              "dog cat eyes like", "i like apple", "apple i hate",
              "apple i movie book music like", "cat dog hate", "cat dog like"]

word_sequence = " ".join(sentences).split()
word_list = " ".join(sentences).split()
word_list = list(set(word_list))
#enumerate是一个枚举的关键词，i是键，w是值，这样就将所有单词按照自然数编成字典
word_dict = {w: i for i, w in enumerate(word_list)}

# Word2Vec Parameter
batch_size = 20  # To show 2 dim embedding graph
embedding_size = 2  # To show 2 dim embedding graph
voc_size = len(word_list)

def random_batch(data, size):
    random_inputs = []
    random_labels = []
    #　随机选取sample
    random_index = np.random.choice(range(len(data)), size, replace=False)

    for i in random_index:
        random_inputs.append(np.eye(voc_size)[data[i][0]])  # target
        random_labels.append(data[i][1])  # context word

    return random_inputs, random_labels

# Make skip gram of one size window
#构建输入的samples
skip_grams = []
for i in range(1, len(word_sequence) - 1):
    target = word_dict[word_sequence[i]]
    context = [word_dict[word_sequence[i - 1]], word_dict[word_sequence[i + 1]]]

    for w in context:
        skip_grams.append([target, w])

# Model
class Word2Vec(nn.Module):
    def __init__(self):
        super(Word2Vec, self).__init__()

        # W and WT is not Traspose relationship
        # 初始化从输入到隐藏层的嵌入矩阵，参数随机初始化在（-1，1]
        self.W = nn.Parameter(-2 * torch.rand(voc_size, embedding_size) + 1).type(dtype) # voc_size > embedding_size Weight
        # 随机初始化从隐藏层到输出层的系数矩阵，参数随机初始化在（-1，1]
        self.WT = nn.Parameter(-2 * torch.rand(embedding_size, voc_size) + 1).type(dtype) # embedding_size > voc_size Weight

    # 前向传播
    def forward(self, X):
        # X : [batch_size, voc_size]
        hidden_layer = torch.matmul(X, self.W) # hidden_layer : [batch_size, embedding_size]
        output_layer = torch.matmul(hidden_layer, self.WT) # output_layer : [batch_size, voc_size]
        return output_layer

model = Word2Vec()

#　定义损失函数和优化
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training
for epoch in range(5000):

    input_batch, target_batch = random_batch(skip_grams, batch_size)

    #　被定义为Varialbe类型的变量可以认为是一种常量，在pytorch反向传播过程中不对其求导
    input_batch = Variable(torch.Tensor(input_batch))
    target_batch = Variable(torch.LongTensor(target_batch))

    optimizer.zero_grad()
    output = model(input_batch)

    # output : [batch_size, voc_size], target_batch : [batch_size] (LongTensor, not one-hot)
    loss = criterion(output, target_batch)
    if (epoch + 1)%1000 == 0:
        print(‘Epoch:‘, ‘%04d‘ % (epoch + 1), ‘cost =‘, ‘{:.6f}‘.format(loss))

    loss.backward()
    optimizer.step()

for i, label in enumerate(word_list):
    # model.parameters()是获取模型的参数
    W, WT = model.parameters()
    x, y = float(W[i][0]), float(W[i][1])
    plt.scatter(x, y)
    plt.annotate(label, xy=(x, y), xytext=(5, 2), textcoords=‘offset points‘, ha=‘right‘, va=‘bottom‘)
plt.show()