机器翻译和数据集机器翻译(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 sys
sys.path.append('/home/kesci/input/d2l9528/')
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 Fdef 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])
from torch.utils import data
from torch import optim
数据预处理
将数据集清洗、转化为神经网络的输入minbatch
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])
字符在计算机里是以编码的形式存在,我们通常所用的空格是 \x20 ,是在标准ASCII可见字符 0x20~0x7e 范围内。
而 \xa0 属于 latin1 (ISO/IEC_8859-1)中的扩展字符集字符,代表不间断空白符nbsp(non-breaking space),超出gbk编码范围,是需要去除的特殊字符。再数据预处理的过程中,我们首先需要对数据进行清洗。
分词
In [4]:
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]
建立词典
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)
载入数据集
def pad(line, max_len, padding_token):
if len(line) > max_len:
return line[:max_len]
return line + [padding_token] * (max_len - len(line))
pad(src_vocab[source[0]], 10, src_vocab.pad)
def build_array(lines, vocab, max_len, is_source):
lines = [vocab[line] for line in lines]
if not is_source:
lines = [[vocab.bos] + line + [vocab.eos] for line in lines]
array = torch.tensor([pad(line, max_len, vocab.pad) for line in lines])
valid_len = (array != vocab.pad).sum(1) #第一个维度
return array, valid_len
def load_data_nmt(batch_size, max_len): # This function is saved in d2l.
src_vocab, tgt_vocab = build_vocab(source), build_vocab(target)
src_array, src_valid_len = build_array(source, src_vocab, max_len, True)
tgt_array, tgt_valid_len = build_array(target, tgt_vocab, max_len, False)
train_data = data.TensorDataset(src_array, src_valid_len, tgt_array, tgt_valid_len)
train_iter = data.DataLoader(train_data, batch_size, shuffle=True)
return src_vocab, tgt_vocab, train_iter
rc_vocab, tgt_vocab, train_iter = load_data_nmt(batch_size=2, max_len=8)
for X, X_valid_len, Y, Y_valid_len, in train_iter:
print('X =', X.type(torch.int32), '\nValid lengths for X =', X_valid_len,
'\nY =', Y.type(torch.int32), '\nValid lengths for Y =', Y_valid_len)
break