Code-Word2Vec

发表于 |
字数统计: 369 | 阅读时长 ≈ 2

图 1

Word2Vec

来源：https://github.com/graykode/nlp-tutorial

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# %%
# code by Tae Hwan Jung @graykode
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt

def random_batch():
    random_inputs = []
    random_labels = []
    random_index = np.random.choice(range(len(skip_grams)), batch_size, replace=False)

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

    return random_inputs, random_labels

# Model
class Word2Vec(nn.Module):
    def __init__(self):
        super(Word2Vec, self).__init__()
        # W and WT is not Traspose relationship
        self.W = nn.Linear(voc_size, embedding_size, bias=False) # voc_size > embedding_size Weight
        self.WT = nn.Linear(embedding_size, voc_size, bias=False) # embedding_size > voc_size Weight

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

if __name__ == '__main__':
    batch_size = 2 # mini-batch size
    embedding_size = 2 # embedding size

    sentences = ["apple banana fruit", "banana orange fruit", "orange banana fruit",
                 "dog cat animal", "cat monkey animal", "monkey dog animal"]

    word_sequence = " ".join(sentences).split()
    word_list = " ".join(sentences).split()
    word_list = list(set(word_list))
    word_dict = {w: i for i, w in enumerate(word_list)}
    voc_size = len(word_list)

    # Make skip gram of one size window
    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 = Word2Vec()

    criterion = nn.CrossEntropyLoss()
    optimizer = optim.Adam(model.parameters(), lr=0.001)

    # Training
    for epoch in range(5000):
        input_batch, target_batch = random_batch()
        input_batch = torch.Tensor(input_batch)
        target_batch = 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):
        W, WT = model.parameters()
        x, y = W[0][i].item(), W[1][i].item()
        plt.scatter(x, y)
        plt.annotate(label, xy=(x, y), xytext=(5, 2), textcoords='offset points', ha='right', va='bottom')
    plt.show()

0%