Skip to content
项目
群组
代码片段
帮助
当前项目
正在载入...
登录 / 注册
切换导航面板
T
Toy-MT-Introduction
概览
Overview
Details
Activity
Cycle Analytics
版本库
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
问题
0
Issues
0
列表
Board
标记
里程碑
合并请求
0
Merge Requests
0
CI / CD
CI / CD
流水线
作业
日程表
图表
维基
Wiki
代码片段
Snippets
成员
Collapse sidebar
Close sidebar
活动
图像
聊天
创建新问题
作业
提交
Issue Boards
Open sidebar
NiuTrans
Toy-MT-Introduction
Commits
fa938afa
Commit
fa938afa
authored
May 05, 2020
by
xiaotong
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
guideline of the book
parent
dfd8a7e5
隐藏空白字符变更
内嵌
并排
正在显示
2 个修改的文件
包含
84 行增加
和
15 行删除
+84
-15
Book/ChapterPreface/ChapterPreface.tex
+3
-3
Book/ChapterPreface/Figures/figure-preface.tex
+81
-12
没有找到文件。
Book/ChapterPreface/ChapterPreface.tex
查看文件 @
fa938afa
...
...
@@ -8,7 +8,7 @@
%----------------------------------------------------------------------------------------
{
\color
{
white
}
空
}
\vspace
{
1
em
}
\vspace
{
0.5
em
}
\begin{center}
{
\Huge
\bfnew
{
导
\ \ \ \
读
}}
\end{center}
...
...
@@ -18,7 +18,7 @@
让计算机进行自然语言的翻译是人类长期的梦想,也是人工智能的终极目标之一。自上世纪九十年代起,机器翻译也迈入了基于统计建模的时代,而发展到今天,深度学习等机器学习方法已经在机器翻译中得到了大量的应用,取得了令人瞩目的进步。
在这个时代背景下,对机器翻译的模型、方法、实现技术进行深入了解是自然语言处理领域研究者和实践者所渴望的。本书全面的回顾了近三十年内机器翻译的技术发展历程,并围绕统计建模和深度学习两个主题对机器翻译的技术方法进行了全面介绍。在写作中,笔者力求用朴实的语言和实例阐述机器翻译的基本
思想
,同时对相关的技术前沿进行讨论。本书可以供计算机相关专业高年级本科生及研究生学习之用,也可以作为自然语言处理,特别是机器翻译相关研究人员的参考资料。
在这个时代背景下,对机器翻译的模型、方法、实现技术进行深入了解是自然语言处理领域研究者和实践者所渴望的。本书全面的回顾了近三十年内机器翻译的技术发展历程,并围绕统计建模和深度学习两个主题对机器翻译的技术方法进行了全面介绍。在写作中,笔者力求用朴实的语言和实例阐述机器翻译的基本
模型和方法
,同时对相关的技术前沿进行讨论。本书可以供计算机相关专业高年级本科生及研究生学习之用,也可以作为自然语言处理,特别是机器翻译相关研究人员的参考资料。
本书共分为七个章节。章节的顺序参考了机器翻译技术发展的时间脉络,同时兼顾形成机器翻译知识体系的内在逻辑。各章节的主要内容包括:
...
...
@@ -42,7 +42,7 @@
其中,第一章是对机器翻译的整体介绍。第二章和第五章是对统计建模和深度学习方法的介绍,分别建立了两个机器翻译范式的基础知识体系
\ \dash
\
统计机器翻译和神经机器翻译。统计机器翻译部分(第三、四章)涉及早期的基于单词的翻译模型,以及本世纪初流行的基于短语和句法的翻译模型;神经机器翻译(第六、七章)代表了当今机器翻译的前沿,内容主要涉及了基于端到端表示学习的机器翻译建模方法。特别是,第七章对一些先进的神经机器翻译方法进行了讨论,为相关相关科学问题的研究和实用系统的开发提供了可落地的思路。图
\ref
{
fig:preface
}
展示了本书各个章节及核心概念之间的关系。
{
\red
用最简单的方式阐述机器翻译的基本思想
}
是笔者所期望达到的目标。但是,书中难免会涉及一些概念形式化定义和算法的抽象描述,笔者
也都尽所能通过图例进行解释(本书共320张插图)。不过,本书所包含的内容较为广泛,难免有疏漏之处
,望读者海涵,并指出不当之处。
{
\red
用最简单的方式阐述机器翻译的基本思想
}
是笔者所期望达到的目标。但是,书中难免会涉及一些概念形式化定义和算法的抽象描述,笔者
尽所能通过图例进行解释(本书共320张插图)。不过,本书所包含的内容较为广泛,难免会有疏漏
,望读者海涵,并指出不当之处。
\begin{figure}
[htp]
\centering
...
...
Book/ChapterPreface/Figures/figure-preface.tex
查看文件 @
fa938afa
% !Mode:: "TeX:UTF-8"
% !TEX encoding = UTF-8 Unicode
\begin{tikzpicture}
\tikzstyle
{
secnode
}
=[font=
\scriptsize
,minimum height=4.0em,minimum width=22em,draw,thick,fill=white,drop shadow]
...
...
@@ -7,34 +10,101 @@
% section 1
\node
[secnode,anchor=south west,minimum width=22.5em,red,fill=white] (sec1) at (0,0)
{}
;
\node
[anchor=north] (sec1label) at ([yshift=-0.2em]sec1.north)
{
\small
{
机器翻译简介
}}
;
\node
[anchor=north west,draw=red,thick,fill=white,rounded corners] (sec1title) at ([xshift=-0.3em,yshift=0.3em]sec1.north west)
{{
\footnotesize\bfnew
{
\color
{
red
}
第一章
}}}
;
\node
[conceptnode,anchor=south west,fill=red!15,thin] (sec1box1) at ([xshift=0.5em,yshift=0.5em]sec1.south west)
{
\footnotesize
{
发展历史
}}
;
\node
[conceptnode,anchor=west,fill=red!15,thin] (sec1box2) at ([xshift=0.5em]sec1box1.east)
{
\footnotesize
{
评价方法
}}
;
\node
[conceptnode,anchor=west,fill=red!15,thin] (sec1box3) at ([xshift=0.5em]sec1box2.east)
{
\footnotesize
{
应用情况
}}
;
\node
[conceptnode,anchor=west,fill=red!15,thin] (sec1box4) at ([xshift=0.5em]sec1box3.east)
{
\footnotesize
{
系统
\&
数据
}}
;
\node
[anchor=north west,draw,thick,fill=white,red,rounded corners] (sec1title) at ([xshift=-0.3em,yshift=0.3em]sec1.north west)
{{
\footnotesize\bfnew
{
第一章
}}}
;
% section 2
\node
[secnode,anchor=south,blue,fill=white] (sec2) at ([xshift=-6.5em,yshift=3em]sec1.north)
{}
;
\node
[anchor=north] (sec2label) at (sec2.north)
{
\small
{
词法、语法及统计建模基础
}}
;
\node
[conceptnode,anchor=south west,fill=blue!15,thin,minimum width=4em,align=left] (sec2box1) at ([xshift=0.5em,yshift=0.4em]sec2.south west)
{
\tiny
{
概率论与
}
\\\tiny
{
统计建模基础
}}
;
\node
[anchor=north west,draw=blue,thick,fill=white,rounded corners] (sec2title) at ([xshift=-0.3em,yshift=0.3em]sec2.north west)
{{
\footnotesize\bfnew
{
\color
{
blue
}
第二章
}}}
;
\node
[conceptnode,anchor=south west,fill=ublue!15,thin,minimum width=4em,align=left] (sec2box1) at ([xshift=0.5em,yshift=0.4em]sec2.south west)
{
\tiny
{
概率论与
}
\\\tiny
{
统计建模基础
}}
;
\node
[anchor=west,draw,dotted,thick,minimum height=2em,minimum width=16.6em,align=left] (sec2box2) at ([xshift=0.3em]sec2box1.east)
{}
;
\node
[conceptnodesmall,minimum width=5em,anchor=south west,fill=blue!15,thin] (sec2box3) at ([xshift=0.4em,yshift=0.3em]sec2box2.south west)
{
\scriptsize
{
中文分词
}}
;
\node
[conceptnodesmall,minimum width=5em,anchor=west,fill=blue!15,thin] (sec2box4) at ([xshift=0.4em]sec2box3.east)
{
\scriptsize
{$
n
$
元语法模型
}}
;
\node
[conceptnodesmall,minimum width=5em,anchor=west,fill=blue!15,thin] (sec2box5) at ([xshift=0.4em]sec2box4.east)
{
\scriptsize
{
句法分析
}}
;
\node
[anchor=north west,draw,thick,fill=white,blue,rounded corners] (sec2title) at ([xshift=-0.3em,yshift=0.3em]sec2.north west)
{{
\footnotesize\bfnew
{
第二章
}}}
;
\draw
[->,very thick] ([xshift=2em,yshift=0.2em]sec1.north) .. controls +(north:2.5em) and +(south:2.5em) .. ([xshift=-0em,yshift=-0.2em]sec2.south);
\draw
[->,very thick] ([xshift=-1em,yshift=0.2em]sec1.north) .. controls +(north:2.5em) and +(south:2.5em) .. ([xshift=-3em,yshift=-0.2em]sec2.south);
% section 5
\node
[secnode,anchor=south,orange,fill=white] (sec5) at ([xshift=7em,yshift=10em]sec1.north)
{}
;
\node
[anchor=north] (sec5label) at (sec5.north)
{
\small
{
人工神经网络和神经语言建模
}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=orange!15,thin,minimum width=4em,align=left] (sec5box1) at ([xshift=0.5em,yshift=0.4em]sec5.south west)
{
\tiny
{
线性代数基础
}
\\\tiny
{
与感知机
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=orange!15,thin,minimum width=4em,align=left] (sec5box2) at ([xshift=0.2em]sec5box1.east)
{
\tiny
{
多层神经网络
}
\\\tiny
{
与实现方法
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=orange!15,thin,minimum width=4em,align=left] (sec5box3) at ([xshift=0.2em]sec5box2.east)
{
\tiny
{
模型训练
}
\\\tiny
{
(反向传播)
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=ublue!15,thin,minimum width=4em,align=left] (sec5box4) at ([xshift=0.2em]sec5box3.east)
{
\tiny
{
神经语言模型
}
\\\tiny
{
(FNN等)
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=ublue!15,thin,minimum width=4em,align=left] (sec5box5) at ([xshift=0.2em]sec5box4.east)
{
\tiny
{
表示学习与
}
\\\tiny
{
预训练模型
}}
;
\node
[anchor=north west,draw,thick,fill=white,orange,rounded corners] (sec5title) at ([xshift=-0.3em,yshift=0.3em]sec5.north west)
{{
\footnotesize\bfnew
{
第五章
}}}
;
\node
[anchor=north west,draw=orange,thick,fill=white,rounded corners] (sec5title) at ([xshift=-0.3em,yshift=0.3em]sec5.north west)
{{
\footnotesize\bfnew
{
\color
{
orange
}
第五章
}}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=orange!15,thin,align=left] (sec5box1) at ([xshift=0.5em,yshift=0.4em]sec5.south west)
{
\tiny
{
线性代数基础
}
\\\tiny
{
与感知机
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=orange!15,thin,align=left] (sec5box2) at ([xshift=0.2em]sec5box1.east)
{
\tiny
{
多层神经网络
}
\\\tiny
{
与实现方法
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=orange!15,thin,align=left] (sec5box3) at ([xshift=0.2em]sec5box2.east)
{
\tiny
{
模型训练
}
\\\tiny
{
(反向传播)
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=purple!15,thin,align=left] (sec5box4) at ([xshift=0.2em]sec5box3.east)
{
\tiny
{
神经语言模型
}
\\\tiny
{
(FNN等)
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=purple!15,thin,align=left] (sec5box5) at ([xshift=0.2em]sec5box4.east)
{
\tiny
{
表示学习与
}
\\\tiny
{
预训练模型
}}
;
\node
[draw,dotted,thick,inner sep=1pt] [fit = (sec5box4) (sec5box5)] (pretrainbox)
{}
;
\draw
[->,very thick] ([yshift=-9.8em]sec5.south) -- ([yshift=-0.2em]sec5.south);
\end{tikzpicture}
\ No newline at end of file
% section 3
\node
[secnode,anchor=south,ugreen,fill=white] (sec3) at ([yshift=10em]sec2.north)
{}
;
\node
[anchor=north] (sec3label) at (sec3.north)
{
\small
{
基于词的机器翻译模型
}}
;
\node
[anchor=north west,draw=ugreen,thick,fill=white,rounded corners] (sec3title) at ([xshift=-0.3em,yshift=0.3em]sec3.north west)
{{
\footnotesize\bfnew
{
\color
{
ugreen
}
第三章
}}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=ublue!15,thin,align=left] (sec3box1) at ([xshift=0.5em,yshift=0.4em]sec3.south west)
{
\tiny
{
机器翻译的统计
}
\\\tiny
{
描述(实例)
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left] (sec3box2) at ([xshift=0.2em]sec3box1.east)
{
\tiny
{
噪声信道模型
}
\\\tiny
{
与生成式模型
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left] (sec3box3) at ([xshift=0.2em]sec3box2.east)
{
\tiny
{
IBM模型、隐
}
\\\tiny
{
马尔可夫模型
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left] (sec3box4) at ([xshift=0.2em]sec3box3.east)
{
\tiny
{
\hspace
{
0.9em
}
参数学习
}
\\\tiny
{
=优化
}}
;
\node
[conceptnode,minimum width=3.8em,anchor=west,fill=green!20,thin,align=left,minimum height=2em,inner sep=2pt] (sec3box5) at ([xshift=0.2em]sec3box4.east)
{
\scriptsize
{
EM算法
}}
;
\draw
[->,very thick] ([yshift=0.2em,xshift=-3em]sec2.north) -- ([yshift=-0.2em,xshift=-3em]sec3.south);
% section 4
\node
[secnode,anchor=south,ugreen,fill=white] (sec4) at ([yshift=3em]sec3.north)
{}
;
\node
[anchor=north] (sec4label) at (sec4.north)
{
\small
{
基于短语和句法的机器翻译模型
}}
;
\node
[anchor=north west,draw=ugreen,thick,fill=white,rounded corners] (sec4title) at ([xshift=-0.3em,yshift=0.3em]sec4.north west)
{{
\footnotesize\bfnew
{
\color
{
ugreen
}
第四章
}}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=ublue!15,thin,align=left] (sec4box1) at ([xshift=0.5em,yshift=0.4em]sec4.south west)
{
\tiny
{
判别式模型与
}
\\\tiny
{
最小错误率训练
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left] (sec4box2) at ([xshift=0.2em]sec4box1.east)
{
\tiny
{
基于翻译推导
}
\\\tiny
{
的建模
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left] (sec4box3) at ([xshift=0.2em]sec4box2.east)
{
\tiny
{
短语及句法
}
\\\tiny
{
翻译规则抽取
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=green!20,thin,align=left,minimum height=2em,inner sep=2pt] (sec4box4) at ([xshift=0.2em]sec4box3.east)
{
\scriptsize
{
调序模型
}}
;
\node
[conceptnode,minimum width=3.8em,anchor=west,fill=green!20,thin,align=left,minimum height=2em,inner sep=2pt] (sec4box5) at ([xshift=0.2em]sec4box4.east)
{
\scriptsize
{
解码
}}
;
\draw
[->,very thick] ([yshift=0.2em,xshift=-3em]sec3.north) -- ([yshift=-0.2em,xshift=-3em]sec4.south);
% section 6
\node
[secnode,anchor=south,purple,fill=white] (sec6) at ([yshift=19em]sec5.north)
{}
;
\node
[anchor=north] (sec6label) at (sec6.north)
{
\small
{
神经机器翻译模型
}}
;
\node
[anchor=north west,draw=purple,thick,fill=white,rounded corners] (sec6title) at ([xshift=-0.3em,yshift=0.3em]sec6.north west)
{{
\footnotesize\bfnew
{
\color
{
purple
}
第六章
}}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=ublue!15,thin,align=left] (sec6box1) at ([xshift=0.5em,yshift=0.4em]sec6.south west)
{
\tiny
{
编码器-解码器
}
\\\tiny
{
框架
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=ublue!15,thin,align=left,minimum height=2em] (sec6box2) at ([xshift=0.2em]sec6box1.east)
{
\scriptsize
{
注意力机制
}}
;
\node
[conceptnode,minimum width=7.5em,anchor=west,fill=purple!15,thin,align=left] (sec6box3) at ([xshift=0.2em]sec6box2.east)
{
\tiny
{
基于RNN和Transformer
}
\\\tiny
{
的神经机器翻译建模
}}
;
\node
[conceptnode,minimum width=4em,anchor=west,fill=purple!15,thin,align=left,minimum height=2em] (sec6box4) at ([xshift=0.2em]sec6box3.east)
{
\scriptsize
{
训练与推断
}}
;
\draw
[->,very thick] ([yshift=0.2em]sec5.north) -- ([yshift=-0.2em]sec6.south);
\draw
[->,very thick,dotted] ([yshift=0.2em,xshift=-2em]sec4.north) .. controls +(north:5.0em) and +(west:4em) .. ([xshift=-0.2em]sec6.west);
\draw
[->,thick,dotted] ([xshift=3em,yshift=0.2em]pretrainbox.north) .. controls +(north:15em) and +(south:15em) .. ([xshift=0em,yshift=-0.0em]sec6box3.south);
% section 7
\node
[secnode,anchor=south,purple,fill=white,minimum height=6.3em] (sec7) at ([yshift=3em]sec6.north)
{}
;
\node
[anchor=north] (sec7label) at (sec7.north)
{
\small
{
神经机器翻译实战
\ \dash
\
参加一次比赛
}}
;
\node
[anchor=north west,draw=purple,thick,fill=white,rounded corners] (sec7title) at ([xshift=-0.3em,yshift=0.3em]sec7.north west)
{{
\footnotesize\bfnew
{
\color
{
purple
}
第七章
}}}
;
\node
[conceptnode,minimum width=4em,anchor=south west,fill=ublue!15,thin,align=left,minimum height=4.2em] (sec7box1) at ([xshift=0.5em,yshift=0.4em]sec7.south west)
{
\tiny
{
数据处理、
}
\\\tiny
{
子词切分
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box2) at ([xshift=0.5em,yshift=-0.2em]sec7box1.north east)
{
\tiny
{
正则化
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box3) at ([yshift=-0.1em]sec7box2.south west)
{
\tiny
{
增大模型容量
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box4) at ([yshift=-0.1em]sec7box3.south west)
{
\tiny
{
大批量训练
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box5) at ([xshift=0.6em]sec7box2.north east)
{
\tiny
{
推断优化
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box6) at ([yshift=-0.1em]sec7box5.south west)
{
\tiny
{
译文长度控制
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box7) at ([yshift=-0.1em]sec7box6.south west)
{
\tiny
{
多模型集成
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box8) at ([xshift=0.6em]sec7box5.north east)
{
\tiny
{
深层模型
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box9) at ([yshift=-0.1em]sec7box8.south west)
{
\tiny
{
知识精炼
}}
;
\node
[anchor=north west,minimum width=5em,anchor=north west,fill=purple!15] (sec7box10) at ([yshift=-0.1em]sec7box9.south west)
{
\tiny
{
单语数据使用
}}
;
\node
[draw,dotted,thick,inner sep=1pt] [fit = (sec7box2) (sec7box3) (sec7box4)] (trainbox)
{}
;
\node
[draw,dotted,thick,inner sep=1pt] [fit = (sec7box5) (sec7box6) (sec7box7)] (inferencebox)
{}
;
\node
[draw,dotted,thick,inner sep=1pt] [fit = (sec7box8) (sec7box9) (sec7box10)] (advancedbox)
{}
;
\draw
[->,very thick] ([yshift=0.2em]sec6.north) -- ([yshift=-0.2em]sec7.south);
\draw
[->,very thick,dotted] ([yshift=0.2em,xshift=-3em]sec4.north) .. controls +(north:7.0em) and +(west:6em) .. ([xshift=-0.2em]sec7.west);
\end{tikzpicture}
编写
预览
Markdown
格式
0%
重试
或
添加新文件
添加附件
取消
您添加了
0
人
到此讨论。请谨慎行事。
请先完成此评论的编辑!
取消
请
注册
或者
登录
后发表评论