文本预处理、语言模型、循环神经网络基础

文本预处理

通过对文章的处理将词或者字来进行处理，建立有索引的标签以及保留词频，是自然语言处理的重要一步、也是最开始的一步。
首先读入文件

import collections
import re

def read_time_machine():
    with open('/home/kesci/input/timemachine7163/timemachine.txt', 'r') as f:
        lines = [re.sub('[^a-z]+', ' ', line.strip().lower()) 
    #将除了a-z之外的所有东西全都替换为空格
    for line in f]
    return lines


lines = read_time_machine()
print('# sentences %d' % len(lines))

分词

def tokenize(sentences, token='word'):
	# 分为词或者字
    """Split sentences into word or char tokens"""
    if token == 'word':
        return [sentence.split(' ') for sentence in sentences]
    elif token == 'char':
        return [list(sentence) for sentence in sentences]
    else:
        print('ERROR: unkown token type '+token)

tokens = tokenize(lines)
tokens[0:2]

建立字典，将字符串转换为序列，我们需要构建一个词典，将每个词映射到一个唯一的索引编号

class Vocab(object):
    def __init__(self, tokens, min_freq=0, use_special_tokens=False):
        counter = count_corpus(tokens)  # : 
        self.token_freqs = list(counter.items())
        self.idx_to_token = []
        if use_special_tokens:
            # padding, begin of sentence, end of sentence, unknown
            self.pad, self.bos, self.eos, self.unk = (0, 1, 2, 3)
            self.idx_to_token += ['', '', '', '']
        else:
            self.unk = 0
            self.idx_to_token += ['']
        self.idx_to_token += [token for token, freq in self.token_freqs
                        if freq >= min_freq and token not in self.idx_to_token]
        self.token_to_idx = dict()
        for idx, token in enumerate(self.idx_to_token):
            self.token_to_idx[token] = idx

    def __len__(self):
        return len(self.idx_to_token)

    def __getitem__(self, tokens):
        if not isinstance(tokens, (list, tuple)):
            return self.token_to_idx.get(tokens, self.unk)
        return [self.__getitem__(token) for token in tokens]

    def to_tokens(self, indices):
        if not isinstance(indices, (list, tuple)):
            return self.idx_to_token[indices]
        return [self.idx_to_token[index] for index in indices]

def count_corpus(sentences):
    tokens = [tk for st in sentences for tk in st]
    return collections.Counter(tokens)  # 返回一个字典，记录每个词的出现次数在这里插入代码片

用现有工具进行分词
spacy与nltk

text = "Mr. Chen doesn't agree with my suggestion."
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(text)
print([token.text for token in doc])

[‘Mr.’, ‘Chen’, ‘does’, “n’t”, ‘agree’, ‘with’, ‘my’, ‘suggestion’, ‘.’]

text = "Mr. Chen doesn't agree with my suggestion."
from nltk.tokenize import word_tokenize
from nltk import data
data.path.append('/home/kesci/input/nltk_data3784/nltk_data')
print(word_tokenize(text))

[‘Mr.’, ‘Chen’, ‘does’, “n’t”, ‘agree’, ‘with’, ‘my’, ‘suggestion’, ‘.’]

语言模型

在这里我们主要讲解n-gram模型
假设每个词都是依靠前一个词依次生成的，例如一段含有四个词的文本序列的概率就是

根据n 元语法通过马尔可夫假设简化模型，马尔科夫假设是指一个词的出现只与前面n个词相关，即 n 阶马尔可夫链
公式为：

循环神经网络基础

下图展现了如何用循环神经网络实现语言模型。我们的目标是基于当前的输入与过去的输入序列，预测当下的一个字符。循环神经网络引入一个隐藏变量$H$，用$H_t$表示H在t时间的值，根据下题可知，$H_t$的计算屈居于输入$X_t$与$H_{t-1}$