task04

机器翻译及相关技术

机器翻译（MT）：将一段文本从一种语言自动翻译为另一种语言，用神经网络解决这个问题通常称为神经机器翻译（NMT）。
主要特征：输出是单词序列而不是单个单词。 输出序列的长度可能与源序列的长度不同。

import os
import sys
import collections
import d2l
import zipfile
from d2l.data.base import Vocab
import time
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils import data
from torch import optim


sys.path.append('/home/kesci/input/d2l9528/')

# 将数据集清洗、转化为神经网络的输入minbatch
with open('/home/kesci/input/fraeng6506/fra.txt', 'r') as f:
      raw_text = f.read()

def preprocess_raw(text):
    text = text.replace('\u202f', ' ').replace('\xa0', ' ')
    out = ''
    for i, char in enumerate(text.lower()):
        if char in (',', '!', '.') and i > 0 and text[i-1] != ' ':
            out += ' '
        out += char
    return out

text = preprocess_raw(raw_text)
print(text[0:1000])


# 分词 字符串---单词组成的列表
num_examples = 50000
source, target = [], []
for i, line in enumerate(text.split('\n')):
    if i > num_examples:
        break
    parts = line.split('\t')
    if len(parts) >= 2:
        source.append(parts[0].split(' '))
        target.append(parts[1].split(' '))
        
source[0:3], target[0:3]

# 画图
# d2l.set_figsize()
# d2l.plt.hist([[len(l) for l in source], [len(l) for l in target]],label=['source', 'target'])
# d2l.plt.legend(loc='upper right');


# 建立词典 单词组成的列表---单词id组成的列表
def build_vocab(tokens):
    tokens = [token for line in tokens for token in line]
    return d2l.data.base.Vocab(tokens, min_freq=3, use_special_tokens=True)

src_vocab = build_vocab(source)
len(src_vocab)

# show: ![Image Name](https://cdn.kesci.com/upload/image/q5jc5ga5gy.png?imageView2/0/w/960/h/960)

Encoder-Decoder:

    encoder：输入到隐藏状态  
    decoder：隐藏状态到输出

Image Name

class Encoder(nn.Module):
    def __init__(self, **kwargs):
        super(Encoder, self).__init__(**kwargs)

    def forward(self, X, *args):
        raise NotImplementedError


class Decoder(nn.Module):
    def __init__(self, **kwargs):
        super(Decoder, self).__init__(**kwargs)

    def init_state(self, enc_outputs, *args):
        raise NotImplementedError

    def forward(self, X, state):
        raise NotImplementedError


class EncoderDecoder(nn.Module):
    def __init__(self, encoder, decoder, **kwargs):
        super(EncoderDecoder, self).__init__(**kwargs)
        self.encoder = encoder
        self.decoder = decoder

    def forward(self, enc_X, dec_X, *args):
        enc_outputs = self.encoder(enc_X, *args)
        dec_state = self.decoder.init_state(enc_outputs, *args)
        return self.decoder(dec_X, dec_state)

Sequence to Sequence模型
模型：
训练

Image Name
预测
Image Name

具体结构：

Image Name

Encoder

class Seq2SeqEncoder(d2l.Encoder):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0, **kwargs):
        super(Seq2SeqEncoder, self).__init__(**kwargs)
        self.num_hiddens=num_hiddens
        self.num_layers=num_layers
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.LSTM(embed_size,num_hiddens, num_layers, dropout=dropout)
   
    def begin_state(self, batch_size, device):
        return [torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens),  device=device),
                torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens),  device=device)]
    def forward(self, X, *args):
        X = self.embedding(X) # X shape: (batch_size, seq_len, embed_size)
        X = X.transpose(0, 1)  # RNN needs first axes to be time
        # state = self.begin_state(X.shape[1], device=X.device)
        out, state = self.rnn(X)
        # The shape of out is (seq_len, batch_size, num_hiddens).
        # state contains the hidden state and the memory cell
        # of the last time step, the shape is (num_layers, batch_size, num_hiddens)
        return out, state

Decoder:

class Seq2SeqDecoder(d2l.Decoder):
   
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0, **kwargs):
        super(Seq2SeqDecoder, self).__init__(**kwargs)
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.LSTM(embed_size,num_hiddens, num_layers, dropout=dropout)
        self.dense = nn.Linear(num_hiddens,vocab_size)

    def init_state(self, enc_outputs, *args):
        return enc_outputs[1]

    def forward(self, X, state):
        X = self.embedding(X).transpose(0, 1)
        out, state = self.rnn(X, state)
        # Make the batch to be the first dimension to simplify loss computation.
        out = self.dense(out).transpose(0, 1)
        return out, state

注意力机制与Seq2seq模型

在“编码器—解码器（seq2seq）”⼀节⾥，解码器在各个时间步依赖相同的背景变量（context vector）来获取输⼊序列信息。当编码器为循环神经⽹络时，背景变量来⾃它最终时间步的隐藏状态。将源序列输入信息以循环单位状态编码，然后将其传递给解码器以生成目标序列。然而这种结构存在着问题，尤其是RNN机制实际中存在长程梯度消失的问题，对于较长的句子，我们很难寄希望于将输入的序列转化为定长的向量而保存所有的有效信息，所以随着所需翻译句子的长度的增加，这种结构的效果会显著下降。

与此同时，解码的目标词语可能只与原输入的部分词语有关，而并不是与所有的输入有关。例如，当把“Hello world”翻译成“Bonjour le monde”时，“Hello”映射成“Bonjour”，“world”映射成“monde”。在seq2seq模型中，解码器只能隐式地从编码器的最终状态中选择相应的信息。然而，注意力机制可以将这种选择过程显式地建模。

Image Name

注意力机制框架:

Attention 是一种通用的带权池化方法，输入由两部分构成：询问（query）和键值对（key-value pairs）。. Query , attention layer得到输出与value的维度一致 . 对于一个query来说，attention layer 会与每一个key计算注意力分数并进行权重的归一化，输出的向量则是value的加权求和，而每个key计算的权重与value一一对应。

为了计算输出，我们首先假设有一个函数 用于计算query和key的相似性，然后可以计算所有的 attention scores by

我们使用 softmax函数 获得注意力权重：

最终的输出就是value的加权求和：

Image Name

不同的attetion layer的区别在于score函数的选择，在本节的其余部分，我们将讨论两个常用的注意层 Dot-product Attention 和 Multilayer Perceptron Attention；随后我们将实现一个引入attention的seq2seq模型并在英法翻译语料上进行训练与测试。

Transformer

为了整合CNN和RNN的优势，[Vaswani et al., 2017] 创新性地使用注意力机制设计了Transformer模型。该模型利用attention机制实现了并行化捕捉序列依赖，并且同时处理序列的每个位置的tokens，上述优势使得Transformer模型在性能优异的同时大大减少了训练时间。

图10.3.1展示了Transformer模型的架构，与9.7节的seq2seq模型相似，Transformer同样基于编码器-解码器架构，其区别主要在于以下三点：

1. Transformer blocks：将seq2seq模型重的循环网络替换为了Transformer Blocks，该模块包含一个多头注意力层（Multi-head Attention Layers）以及两个position-wise feed-forward networks（FFN）。对于解码器来说，另一个多头注意力层被用于接受编码器的隐藏状态。
2. Add and norm：多头注意力层和前馈网络的输出被送到两个“add and norm”层进行处理，该层包含残差结构以及层归一化。
3. Position encoding：由于自注意力层并没有区分元素的顺序，所以一个位置编码层被用于向序列元素里添加位置信息。

Fig. 10.3.1 The Transformer architecture.

import os
import math
import sys
sys.path.append('/home/kesci/input/d2len9900')

import numpy as np
import torch 
import torch.nn as nn
import torch.nn.functional as F

import d2l


def SequenceMask(X, X_len,value=-1e6):
    maxlen = X.size(1)
    X_len = X_len.to(X.device)
    #print(X.size(),torch.arange((maxlen),dtype=torch.float)[None, :],'\n',X_len[:, None] )
    mask = torch.arange((maxlen), dtype=torch.float, device=X.device)
    mask = mask[None, :] < X_len[:, None]
    #print(mask)
    X[~mask]=value
    return X

def masked_softmax(X, valid_length):
    # X: 3-D tensor, valid_length: 1-D or 2-D tensor
    softmax = nn.Softmax(dim=-1)
    if valid_length is None:
        return softmax(X)
    else:
        shape = X.shape
        if valid_length.dim() == 1:
            try:
                valid_length = torch.FloatTensor(valid_length.numpy().repeat(shape[1], axis=0))#[2,2,3,3]
            except:
                valid_length = torch.FloatTensor(valid_length.cpu().numpy().repeat(shape[1], axis=0))#[2,2,3,3]
        else:
            valid_length = valid_length.reshape((-1,))
        # fill masked elements with a large negative, whose exp is 0
        X = SequenceMask(X.reshape((-1, shape[-1])), valid_length)
 
        return softmax(X).reshape(shape)

# Save to the d2l package.
class DotProductAttention(nn.Module): 

    def __init__(self, dropout, **kwargs):
        super(DotProductAttention, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)

    # query: (batch_size, #queries, d)
    # key: (batch_size, #kv_pairs, d)
    # value: (batch_size, #kv_pairs, dim_v)
    # valid_length: either (batch_size, ) or (batch_size, xx)
    def forward(self, query, key, value, valid_length=None):
        d = query.shape[-1]
        # set transpose_b=True to swap the last two dimensions of key
        scores = torch.bmm(query, key.transpose(1,2)) / math.sqrt(d)
        attention_weights = self.dropout(masked_softmax(scores, valid_length))
        return torch.bmm(attention_weights, value)

# 多头注意力层
class MultiHeadAttention(nn.Module):
    def __init__(self, input_size, hidden_size, num_heads, dropout, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        self.num_heads = num_heads
        self.attention = DotProductAttention(dropout)
        self.W_q = nn.Linear(input_size, hidden_size, bias=False)
        self.W_k = nn.Linear(input_size, hidden_size, bias=False)
        self.W_v = nn.Linear(input_size, hidden_size, bias=False)
        self.W_o = nn.Linear(hidden_size, hidden_size, bias=False)
    
    def forward(self, query, key, value, valid_length):
        # query, key, and value shape: (batch_size, seq_len, dim),
        # where seq_len is the length of input sequence
        # valid_length shape is either (batch_size, )
        # or (batch_size, seq_len).

        # Project and transpose query, key, and value from
        # (batch_size, seq_len, hidden_size * num_heads) to
        # (batch_size * num_heads, seq_len, hidden_size).
        
        query = transpose_qkv(self.W_q(query), self.num_heads)
        key = transpose_qkv(self.W_k(key), self.num_heads)
        value = transpose_qkv(self.W_v(value), self.num_heads)
        
        if valid_length is not None:
            # Copy valid_length by num_heads times
            device = valid_length.device
            valid_length = valid_length.cpu().numpy() if valid_length.is_cuda else valid_length.numpy()
            if valid_length.ndim == 1:
                valid_length = torch.FloatTensor(np.tile(valid_length, self.num_heads))
            else:
                valid_length = torch.FloatTensor(np.tile(valid_length, (self.num_heads,1)))

            valid_length = valid_length.to(device)
            
        output = self.attention(query, key, value, valid_length)
        output_concat = transpose_output(output, self.num_heads)
        return self.W_o(output_concat)


def transpose_qkv(X, num_heads):
    # Original X shape: (batch_size, seq_len, hidden_size * num_heads),
    # -1 means inferring its value, after first reshape, X shape:
    # (batch_size, seq_len, num_heads, hidden_size)
    X = X.view(X.shape[0], X.shape[1], num_heads, -1)
    
    # After transpose, X shape: (batch_size, num_heads, seq_len, hidden_size)
    X = X.transpose(2, 1).contiguous()

    # Merge the first two dimensions. Use reverse=True to infer shape from
    # right to left.
    # output shape: (batch_size * num_heads, seq_len, hidden_size)
    output = X.view(-1, X.shape[2], X.shape[3])
    return output


# Saved in the d2l package for later use
def transpose_output(X, num_heads):
    # A reversed version of transpose_qkv
    X = X.view(-1, num_heads, X.shape[1], X.shape[2])
    X = X.transpose(2, 1).contiguous()
    return X.view(X.shape[0], X.shape[1], -1)