文本生成介绍

序列对序列

注意力机制

1.加载开发环境

import paddle
import paddle.nn.functional as F
import re
import numpy as np

print(paddle.__version__)
# cpu/gpu环境选择，在 paddle.set_device() 输入对应运行设备。
# device = paddle.set_device('gpu')

2. 统计数据集信息，确定句子长度

我们采用包含90%句子长度的长度值作为句子的长度

# 统计数据集中句子的长度等信息
lines =  open('data/data78721/cmn.txt','r',encoding='utf-8').readlines()
print(len(lines))
datas = []
dic_en = {}
dic_cn = {}
for line in lines:
    ll = line.strip().split('\t')
    if len(ll)<2:
        continue
    datas.append([ll[0].lower().split(' ')[1:-1],list(ll[1])])
    # print(ll[0])
    if len(ll[0].split(' ')) not in dic_en:
        dic_en[len(ll[0].split(' '))] = 1
    else:
        dic_en[len(ll[0].split(' '))] +=1
    if len(ll[1]) not in dic_cn:
        dic_cn[len(ll[1])] = 1
    else:
        dic_cn[len(ll[1])] +=1
keys_en = list(dic_en.keys())
keys_en.sort()
count = 0
# print('英文长度统计：')
for k in keys_en:
    count += dic_en[k]
    # print(k,dic_en[k],count/len(lines))

keys_cn = list(dic_cn.keys())
keys_cn.sort()
count = 0
# print('中文长度统计：')
for k in keys_cn:
    count += dic_cn[k]
    # print(k,dic_cn[k],count/len(lines))
 
en_length = 10
cn_length = 10

3. 构建中文词表、英文词表

# 构建中英文词表
en_vocab = {}
cn_vocab = {}

en_vocab['<pad>'], en_vocab['<bos>'], en_vocab['<eos>'] = 0, 1, 2
cn_vocab['<pad>'], cn_vocab['<bos>'], cn_vocab['<eos>'] = 0, 1, 2
en_idx, cn_idx = 3, 3
for en, cn in datas:
    # print(en,cn)
    for w in en:
        if w not in en_vocab:
            en_vocab[w] = en_idx
            en_idx += 1
    for w in cn:
        if w not in cn_vocab:
            cn_vocab[w] = cn_idx
            cn_idx += 1

print(len(list(en_vocab)))
print(len(list(cn_vocab)))
'''
英文词表长度：6057
中文词表长度：3533
'''

4. 创建数据集

接下来根据词表，我们将会创建一份实际的用于训练的用numpy array组织起来的数据集。

• 所有的句子都通过补充成为了长度相同的句子。
• 对于英文句子（源语言），我们将其反转了过来，这会带来更好的翻译的效果。
• 所创建的padded_cn_label_sents是训练过程中的预测的目标，即，每个中文的当前词去预测下一个词是什么词。

padded_en_sents = []
padded_cn_sents = []
padded_cn_label_sents = []
for en, cn in datas:
    if len(en)>en_length:
        en = en[:en_length]
    if len(cn)>cn_length:
        cn = cn[:cn_length]
    padded_en_sent = en + ['<eos>'] + ['<pad>'] * (en_length - len(en))
    padded_en_sent.reverse()

    padded_cn_sent = ['<bos>'] + cn + ['<eos>'] + ['<pad>'] * (cn_length - len(cn))
    padded_cn_label_sent = cn + ['<eos>'] + ['<pad>'] * (cn_length - len(cn) + 1)
    
    padded_en_sents.append(np.array([en_vocab[w] for w in padded_en_sent]))
    padded_cn_sents.append(np.array([cn_vocab[w] for w in padded_cn_sent]) )
    padded_cn_label_sents.append(np.array([cn_vocab[w] for w in padded_cn_label_sent]))

train_en_sents = np.array(padded_en_sents)
train_cn_sents = np.array(padded_cn_sents)
train_cn_label_sents = np.array(padded_cn_label_sents)
 
print(train_en_sents.shape)
print(train_cn_sents.shape)
print(train_cn_label_sents.shape)

5.构建基于Transformer的机器翻译模型

首先定义超参数，用于后续模型的设计与训练

embedding_size = 128
hidden_size = 512
num_encoder_lstm_layers = 1
en_vocab_size = len(list(en_vocab))
cn_vocab_size = len(list(cn_vocab))
epochs = 20
batch_size = 16

使用TransformerEncoder定义Encoder

# encoder: simply learn representation of source sentence
class Encoder(paddle.nn.Layer):
    def __init__(self,en_vocab_size, embedding_size,num_layers=2,head_number=2,middle_units=512):
        super(Encoder, self).__init__()
        self.emb = paddle.nn.Embedding(en_vocab_size, embedding_size,)
        """
        d_model (int) - 输入输出的维度。
        nhead (int) - 多头注意力机制的Head数量。
        dim_feedforward (int) - 前馈神经网络中隐藏层的大小。
        """
        encoder_layer = paddle.nn.TransformerEncoderLayer(embedding_size, head_number, middle_units)
        self.encoder = paddle.nn.TransformerEncoder(encoder_layer, num_layers) 

    def forward(self, x):
        x = self.emb(x)
        en_out = self.encoder(x)
        return en_out

使用TransformerDecoder定义Decoder

class Decoder(paddle.nn.Layer):
    def __init__(self,cn_vocab_size, embedding_size,num_layers=2,head_number=2,middle_units=512):
        super(Decoder, self).__init__()
        self.emb = paddle.nn.Embedding(cn_vocab_size, embedding_size)
        
        decoder_layer = paddle.nn.TransformerDecoderLayer(embedding_size, head_number, middle_units)
        self.decoder = paddle.nn.TransformerDecoder(decoder_layer, num_layers) 
   
        # for computing output logits
        self.outlinear =paddle.nn.Linear(embedding_size, cn_vocab_size)

    def forward(self, x,  encoder_outputs):
        x = self.emb(x)
        # dec_input, enc_output,self_attn_mask,  cross_attn_mask
        de_out = self.decoder(x, encoder_outputs)
        output = self.outlinear(de_out)
        output = paddle.squeeze(output)
        return  output

训练模型

encoder = Encoder(en_vocab_size, embedding_size)
decoder = Decoder(cn_vocab_size, embedding_size)

opt = paddle.optimizer.Adam(learning_rate=0.0001,
                            parameters=encoder.parameters() + decoder.parameters())

for epoch in range(epochs):
    print("epoch:{}".format(epoch))

    # shuffle training data
    perm = np.random.permutation(len(train_en_sents))
    train_en_sents_shuffled = train_en_sents[perm]
    train_cn_sents_shuffled = train_cn_sents[perm]
    train_cn_label_sents_shuffled = train_cn_label_sents[perm]
    # print(train_en_sents_shuffled.shape[0],train_en_sents_shuffled.shape[1])
    for iteration in range(train_en_sents_shuffled.shape[0] // batch_size):
        x_data = train_en_sents_shuffled[(batch_size*iteration):(batch_size*(iteration+1))]
        sent = paddle.to_tensor(x_data)
        en_repr = encoder(sent)

        x_cn_data = train_cn_sents_shuffled[(batch_size*iteration):(batch_size*(iteration+1))]
        x_cn_label_data = train_cn_label_sents_shuffled[(batch_size*iteration):(batch_size*(iteration+1))]
 
        loss = paddle.zeros([1]) 
        for i in range( cn_length + 2):
            cn_word = paddle.to_tensor(x_cn_data[:,i:i+1])
            cn_word_label = paddle.to_tensor(x_cn_label_data[:,i])

            logits = decoder(cn_word, en_repr)
            step_loss = F.cross_entropy(logits, cn_word_label)
            loss += step_loss

        loss = loss / (cn_length + 2)
        if(iteration % 50 == 0):
            print("iter {}, loss:{}".format(iteration, loss.numpy()))

        loss.backward()
        opt.step()
        opt.clear_grad()

6. 使用上述训练好的模型进行测试

encoder.eval()
decoder.eval()

num_of_exampels_to_evaluate = 10

indices = np.random.choice(len(train_en_sents),  num_of_exampels_to_evaluate, replace=False)
x_data = train_en_sents[indices]
sent = paddle.to_tensor(x_data)
en_repr = encoder(sent)

word = np.array(
    [[cn_vocab['<bos>']]] * num_of_exampels_to_evaluate
)
word = paddle.to_tensor(word)
 

decoded_sent = []
for i in range(cn_length + 2):
    logits  = decoder(word, en_repr)
    word = paddle.argmax(logits, axis=1)
    decoded_sent.append(word.numpy())
    word = paddle.unsqueeze(word, axis=-1)

results = np.stack(decoded_sent, axis=1)
for i in range(num_of_exampels_to_evaluate):
    print('---------------------')
    en_input = " ".join(datas[indices[i]][0])
    ground_truth_translate = "".join(datas[indices[i]][1])
    model_translate = ""
    for k in results[i]:
        w = list(cn_vocab)[k]
        if w != '<pad>' and w != '<eos>':
            model_translate += w
    print(en_input)
    print("true: {}".format(ground_truth_translate))
    print("pred: {}".format(model_translate))