NLP(二十三)使用LSTM进行语言建模以预测最优词
原文链接:http://www.one2know.cn/nlp23/
- N元模型
预测要输入的连续词,比如
如果抽取两个连续的词汇,则称之为二元模型 - 准备工作
数据集使用 Alice in Wonderland
将初始数据提取N-grams
import nltk
import string
with open('alice_in_wonderland.txt', 'r') as content_file:
content = content_file.read()
content2 = " ".join("".join([" " if ch in string.punctuation else ch for ch in content]).split())
tokens = nltk.word_tokenize(content2)
tokens = [word.lower() for word in tokens if len(word)>=2]
N = 3
quads = list(nltk.ngrams(tokens,N))
"""
Return the ngrams generated from a sequence of items, as an iterator.
For example:
>>> from nltk.util import ngrams
>>> list(ngrams([1,2,3,4,5], 3))
[(1, 2, 3), (2, 3, 4), (3, 4, 5)]
"""
newl_app = []
for ln in quads:
new1 = ' '.join(ln)
newl_app.append(new1)
print(newl_app[:3])
输出:
['alice adventures in', 'adventures in wonderland', 'in wonderland alice']
- 如何实现
1.预处理:词转换为词向量
2.创建模型和验证:将输入映射到输出的收敛-发散模型(convergent-divergent)
3.预测:最优词预测 - 代码
from __future__ import print_function
from sklearn.model_selection import train_test_split
import nltk
import numpy as np
import string
with open('alice_in_wonderland.txt', 'r') as content_file:
content = content_file.read()
content2 = " ".join("".join([" " if ch in string.punctuation else ch for ch in content]).split())
tokens = nltk.word_tokenize(content2)
tokens = [word.lower() for word in tokens if len(word)>=2]
N = 3
quads = list(nltk.ngrams(tokens,N))
"""
Return the ngrams generated from a sequence of items, as an iterator.
For example:
>>> from nltk.util import ngrams
>>> list(ngrams([1,2,3,4,5], 3))
[(1, 2, 3), (2, 3, 4), (3, 4, 5)]
"""
newl_app = []
for ln in quads:
new1 = ' '.join(ln)
newl_app.append(new1)
# print(newl_app[:3])
# 将单词向量化
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer() # 词=>词向量
"""
>>> corpus = [
... 'This is the first document.',
... 'This document is the second document.',
... 'And this is the third one.',
... 'Is this the first document?',
... ]
>>> vectorizer = CountVectorizer()
>>> X = vectorizer.fit_transform(corpus)
>>> print(vectorizer.get_feature_names())
['and', 'document', 'first', 'is', 'one', 'second', 'the', 'third', 'this']
>>> print(X.toarray()) # doctest: +NORMALIZE_WHITESPACE
[[0 1 1 1 0 0 1 0 1]
[0 2 0 1 0 1 1 0 1]
[1 0 0 1 1 0 1 1 1]
[0 1 1 1 0 0 1 0 1]]
"""
x_trigm = []
y_trigm = []
for l in newl_app:
x_str = " ".join(l.split()[0:N-1])
y_str = l.split()[N-1]
x_trigm.append(x_str)
y_trigm.append(y_str)
x_trigm_check = vectorizer.fit_transform(x_trigm).todense()
y_trigm_check = vectorizer.fit_transform(y_trigm).todense()
# Dictionaries from word to integer and integer to word
dictnry = vectorizer.vocabulary_
rev_dictnry = {v:k for k,v in dictnry.items()}
X = np.array(x_trigm_check)
Y = np.array(y_trigm_check)
Xtrain, Xtest, Ytrain, Ytest,xtrain_tg,xtest_tg = train_test_split(X, Y,x_trigm, test_size=0.3,random_state=1)
print("X Train shape",Xtrain.shape, "Y Train shape" , Ytrain.shape)
print("X Test shape",Xtest.shape, "Y Test shape" , Ytest.shape)
# Model Building
from keras.layers import Input,Dense,Dropout
from keras.models import Model
np.random.seed(1)
BATCH_SIZE = 128
NUM_EPOCHS = 20
input_layer = Input(shape = (Xtrain.shape[1],),name="input")
first_layer = Dense(1000,activation='relu',name = "first")(input_layer)
first_dropout = Dropout(0.5,name="firstdout")(first_layer)
second_layer = Dense(800,activation='relu',name="second")(first_dropout)
third_layer = Dense(1000,activation='relu',name="third")(second_layer)
third_dropout = Dropout(0.5,name="thirdout")(third_layer)
fourth_layer = Dense(Ytrain.shape[1],activation='softmax',name = "fourth")(third_dropout)
history = Model(input_layer,fourth_layer)
history.compile(optimizer = "adam",loss="categorical_crossentropy",metrics=["accuracy"])
print (history.summary())
# Model Training
history.fit(Xtrain, Ytrain, batch_size=BATCH_SIZE,epochs=NUM_EPOCHS, verbose=1,validation_split = 0.2)
# Model Prediction
Y_pred = history.predict(Xtest)
# 测试
print ("Prior bigram words","|Actual","|Predicted","\n")
import random
NUM_DISPLAY = 10
for i in random.sample(range(len(xtest_tg)),NUM_DISPLAY):
print (i,xtest_tg[i],"|",rev_dictnry[np.argmax(Ytest[i])],"|",rev_dictnry[np.argmax(Y_pred[i])])
输出:
X Train shape (17947, 2559) Y Train shape (17947, 2559)
X Test shape (7692, 2559) Y Test shape (7692, 2559)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) (None, 2559) 0
_________________________________________________________________
first (Dense) (None, 1000) 2560000
_________________________________________________________________
firstdout (Dropout) (None, 1000) 0
_________________________________________________________________
second (Dense) (None, 800) 800800
_________________________________________________________________
third (Dense) (None, 1000) 801000
_________________________________________________________________
thirdout (Dropout) (None, 1000) 0
_________________________________________________________________
fourth (Dense) (None, 2559) 2561559
=================================================================
Total params: 6,723,359
Trainable params: 6,723,359
Non-trainable params: 0
_________________________________________________________________
None
Prior bigram words |Actual |Predicted
595 words don | fit | know
3816 in tone | of | of
5792 queen had | only | been
2757 who seemed | to | to
5393 her and | she | she
4197 heard of | one | its
2464 sneeze were | the | of
1590 done with | said | whiting
3039 and most | things | of
4226 the queen | of | said
训练结果不好,因为单词向量维度太大,为2559,相对而言总数据集的单词太少;除了单词预测,还可以字符预测,每碰到一个空格算一个单词
NLP(二十三)使用LSTM进行语言建模以预测最优词的更多相关文章
- NLP(二十二)使用LSTM进行语言建模以预测最优词
预处理 数据集使用Facebook上的BABI数据集 将文件提取成可训练的数据集,包括:文章 问题 答案 def get_data(infile): stories,questions,answers ...
- C++学习(二十三)(C语言部分)之 指针4
指针 指针 存放地址 只能存放地址 使用 &取地址运算符 *取值 解引用运算符 malloc 申请堆内存 free释放堆内存 1.1 指针 存放的地址(变量地址 常量区的地址 堆区内存首地址 ...
- 一起talk C栗子吧(第一百二十三回:C语言实例--显示变量和函数的地址)
各位看官们,大家好,上一回中咱们说的是多线程的样例.这一回咱们说的样例是:显示变量和函数的地址. 闲话休提,言归正转.让我们一起talk C栗子吧! 在编敲代码时,有时候须要获取程序中变量和函数的地址 ...
- 利用UML语言建模--以图书馆管理系统为例
一.基本信息 标题:利用UML语言建模--以图书馆管理系统为例 时间:2016 出版源:内蒙古科技与经济 领域分类:UML:RFID:图书馆:模型: 二.研究背景 问题定义:建立图书馆管理系统 难点: ...
- 二十三、并发编程之深入解析Condition源码
二十三.并发编程之深入解析Condition源码 一.Condition简介 1.Object的wait和notify/notifyAll方法与Condition区别 任何一个java对象都继承于 ...
- 网络流量预测入门(二)之LSTM介绍
目录 网络流量预测入门(二)之LSTM介绍 LSTM简介 Simple RNN的弊端 LSTM的结构 细胞状态(Cell State) 门(Gate) 遗忘门(Forget Gate) 输入门(Inp ...
- WPF入门教程系列二十三——DataGrid示例(三)
DataGrid的选择模式 默认情况下,DataGrid 的选择模式为“全行选择”,并且可以同时选择多行(如下图所示),我们可以通过SelectionMode 和SelectionUnit 属性来修改 ...
- Bootstrap <基础二十三>页面标题(Page Header)
页面标题(Page Header)是个不错的功能,它会在网页标题四周添加适当的间距.当一个网页中有多个标题且每个标题之间需要添加一定的间距时,页面标题这个功能就显得特别有用.如需使用页面标题(Page ...
- Web 前端开发精华文章推荐(HTML5、CSS3、jQuery)【系列二十三】
<Web 前端开发精华文章推荐>2014年第2期(总第23期)和大家见面了.梦想天空博客关注 前端开发 技术,分享各类能够提升网站用户体验的优秀 jQuery 插件,展示前沿的 HTML5 ...
随机推荐
- web设计_2_灵活的文字
最佳设计:可以让用户自由控制任何页面的文字大小. 浏览器中用户都是可以自定义默认的文字大小的,如果使用 px,用户自行在浏览器设置中改变了文字大小后,网页上是不会变化的.我们不能排除视障用户(如近视) ...
- Linux之TCPIP内核参数
/proc/sys/net目录 参考1.Linux之TCPIP内核参数优化 所有的TCP/IP参数都位于/proc/sys/net目录下(请注意,对/proc/sys/net目录下内容的修改都是临时的 ...
- 【Java】You have an error in your SQL syntax ...
详情如下: You have an error in your SQL syntax; check the manual that corresponds to your MySQL server v ...
- hdoj 4715 Difference Between Primes 素数筛选+二分查找
#include <string.h> #include <stdio.h> const int maxn = 1000006; bool vis[1000006]; int ...
- win10家庭版打开组策略
新建记事本,输入: @echo off pushd "%~dp0" dir /b C:\Windows\servicing\Packages\Microsoft-Windows-G ...
- 关于FFT分析音频的学习
本文部分知识从以下文章学习: https://zhuanlan.zhihu.com/p/19763358 傅里叶变换的知识 https://www.cnblogs.com/RabbitHu/p/FFT ...
- 利用Idea重构功能及Java8语法特性——优化深层嵌套代码
当遇到深层嵌套代码,如for,if,lambda表达式或内部类及这些代码的组合,这时我们可以通过Java 8的语法特性来进行优化. 下面的代码是一个嵌套循环的示例. public MappedFiel ...
- Okhttp3 网络请求框架与 Gson
Maven环境 : <dependency> <groupId>com.squareup.okhttp3</groupId> <artifactId>o ...
- 在Java大环境下.NET程序员如何夺得一线生机
先来看一组数据,从某招聘网站直接检索3-4w的岗位,会看到Java与.NET社会需求量的巨大差异,这里就不再对比高薪的岗位了,.NET的高薪岗位更是少的可怜: 笔者从业十余年,一直是在.NET圈子 ...
- Draw.io
如何给类图增加一个字段? 选中一个字段,然后按 Ctrl +Enter 即可. 参考:Add row to class diagram - stackoverflow