Code-NNLM

发表于 | 分类于 |
字数统计: 369 | 阅读时长 ≈ 2

NNLM

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

NNLM 网络结构图
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
# %%
# code by Tae Hwan Jung @graykode
import torch
import torch.nn as nn
import torch.optim as optim

def make_batch():
    input_batch = []
    target_batch = []

    for sen in sentences:
        word = sen.split() # space tokenizer
        input = [word_dict[n] for n in word[:-1]] # create (1~n-1) as input
        target = word_dict[word[-1]] # create (n) as target, We usually call this 'casual language model'

        input_batch.append(input)
        target_batch.append(target)

    return input_batch, target_batch

# Model
class NNLM(nn.Module):
    def __init__(self):
        super(NNLM, self).__init__()
        self.C = nn.Embedding(n_class, m)
        self.H = nn.Linear(n_step * m, n_hidden, bias=False)
        self.d = nn.Parameter(torch.ones(n_hidden))
        self.U = nn.Linear(n_hidden, n_class, bias=False)
        self.W = nn.Linear(n_step * m, n_class, bias=False)
        self.b = nn.Parameter(torch.ones(n_class))

    def forward(self, X):
        X = self.C(X) # X : [batch_size, n_step, n_class]
        X = X.view(-1, n_step * m) # [batch_size, n_step * n_class]
        tanh = torch.tanh(self.d + self.H(X)) # [batch_size, n_hidden]
        output = self.b + self.W(X) + self.U(tanh) # [batch_size, n_class]
        return output

if __name__ == '__main__':
    n_step = 2 # number of steps, n-1 in paper
    n_hidden = 2 # number of hidden size, h in paper
    m = 2 # embedding size, m in paper

    sentences = ["i like dog", "i love coffee", "i hate milk"]

    word_list = " ".join(sentences).split()
    word_list = list(set(word_list))
    word_dict = {w: i for i, w in enumerate(word_list)}
    number_dict = {i: w for i, w in enumerate(word_list)}
    n_class = len(word_dict)  # number of Vocabulary

    model = NNLM()

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

    input_batch, target_batch = make_batch()
    input_batch = torch.LongTensor(input_batch)
    target_batch = torch.LongTensor(target_batch)

    # Training
    for epoch in range(5000):
        optimizer.zero_grad()
        output = model(input_batch)

        # output : [batch_size, n_class], target_batch : [batch_size]
        loss = criterion(output, target_batch)
        if (epoch + 1) % 1000 == 0:
            print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.6f}'.format(loss))

        loss.backward()
        optimizer.step()

    # Predict
    predict = model(input_batch).data.max(1, keepdim=True)[1]

    # Test
    print([sen.split()[:2] for sen in sentences], '->', [number_dict[n.item()] for n in predict.squeeze()])
0%