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
M
mtbookv2
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
mtbookv2
Commits
b87c1f4e
Commit
b87c1f4e
authored
Sep 10, 2020
by
zhoutao
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
更新第三章检查
parent
c9d57ffd
全部展开
隐藏空白字符变更
内嵌
并排
正在显示
13 个修改的文件
包含
33 行增加
和
33 行删除
+33
-33
Chapter3/Figures/figure-a-simple-pre-processing-process.tex
+1
-1
Chapter3/Figures/figure-crf-to-deal-with-sequence-problems.tex
+3
-3
Chapter3/Figures/figure-evaluation-of-probability-for-grammar.tex
+6
-6
Chapter3/Figures/figure-examples-of-chinese-word-segmentation-based-on-1-gram-model.tex
+6
-6
Chapter3/Figures/figure-mt-system-as-a-black-box.tex
+1
-1
Chapter3/Figures/figure-mt=language-analysis+translation-engine.tex
+3
-3
Chapter3/Figures/figure-perspectives-of-expert-ordinary-and-syntactic-parser.tex
+3
-3
Chapter3/Figures/figure-probability-values-corresponding-to-different-derivations.tex
+3
-3
Chapter3/Figures/figure-process-of-statistical-syntax-analysis.tex
+1
-1
Chapter3/Figures/figure-transition-prob-and-launch-prob-in-coin-toss-game.tex
+1
-1
Chapter3/Figures/figure-word-segmentation-based-on-statistics.tex
+5
-5
Chapter3/chapter3.aux
+0
-0
Chapter3/chapter3.tex
+0
-0
没有找到文件。
Chapter3/Figures/figure-a-simple-pre-processing-process.tex
查看文件 @
b87c1f4e
...
...
@@ -13,7 +13,7 @@
\node
[ugreen] (input) at (0,0)
{
猫喜欢吃鱼
}
;
\node
[draw,thick,anchor=west,ublue] (preprocessing) at ([xshift=1em]input.east)
{
分词系统
}
;
\node
[ugreen,anchor=west] (mtinput) at ([xshift=1em]preprocessing.east)
{
猫/喜欢/吃/鱼
}
;
\node
[draw,thick,anchor=west,ublue] (smt) at ([xshift=1em]mtinput.east)
{
MT
系统
}
;
\node
[draw,thick,anchor=west,ublue] (smt) at ([xshift=1em]mtinput.east)
{
机器翻译
系统
}
;
\node
[anchor=west] (mtoutput) at ([xshift=1em]smt.east)
{
...
}
;
\draw
[->,thick,ublue] ([xshift=0.1em]input.east) -- ([xshift=-0.2em]preprocessing.west);
\draw
[->,thick,ublue] ([xshift=0.2em]preprocessing.east) -- ([xshift=-0.1em]mtinput.west);
...
...
Chapter3/Figures/figure-crf-to-deal-with-sequence-problems.tex
查看文件 @
b87c1f4e
...
...
@@ -5,10 +5,10 @@
\node
[anchor=west,hide]
(y2)at([xshift=2em]y1.east)
{$
y
_
2
$}
;
\node
[anchor=west,hide]
(y3)at([xshift=2em]y2.east)
{$
y
_
3
$}
;
\node
[anchor=west,line width=1pt,inner sep=2pt,minimum size=2em]
(dots)at([xshift=2em]y3.east)
{$
\cdots
$}
;
\node
[anchor=west,hide]
(yn-1)at([xshift=2em]dots.east)
{$
y
_{
n
-
1
}$}
;
\node
[anchor=west,hide]
(yn)at([xshift=2em]yn-1.east)
{$
y
_
n
$}
;
\node
[anchor=west,hide]
(yn-1)at([xshift=2em]dots.east)
{$
y
_{
m
-
1
}$}
;
\node
[anchor=west,hide]
(yn)at([xshift=2em]yn-1.east)
{$
y
_
m
$}
;
\node
[anchor=north,draw,line width=1pt,inner sep=2pt,fill=red!30,minimum height=2em,minimum width=12em]
(see)at ([yshift=-3em,xshift=2em]y3.south)
{$
\mathbf
{
X
}
=(
x
_
1
,x
_
2
,
\ldots
,x
_{
n
-
1
}
,x
_
n
)
$}
;
\node
[anchor=north,draw,line width=1pt,inner sep=2pt,fill=red!30,minimum height=2em,minimum width=12em]
(see)at ([yshift=-3em,xshift=2em]y3.south)
{$
\mathbf
{
X
}
=(
x
_
1
,x
_
2
,
\ldots
,x
_{
m
-
1
}
,x
_
m
)
$}
;
\node
[anchor=south,font=\footnotesize]
at ([yshift=1em,xshift=2em]y3.north)
{
待预测的隐藏状态序列
}
;
\node
[anchor=north,font=\footnotesize]
at ([yshift=-1em]see.south)
{
可见状态序列
}
;
...
...
Chapter3/Figures/figure-evaluation-of-probability-for-grammar.tex
查看文件 @
b87c1f4e
...
...
@@ -56,18 +56,18 @@
\node
[rectangle,draw=ublue, inner sep=0.2em]
[fit = (treebanklabel) (t1n1) (t2w1) (t2wn)] (treebank)
{}
;
\end{pgfonlayer}
\node
[anchor=north west] (math1) at ([xshift=2em]treebank.north east)
{
P
(VP
$
\to
$
VV NN)
}
;
\node
[anchor=north west] (math1part2) at ([xshift=-1em,yshift=0.2em]math1.south west)
{$
=
\frac
{
\textrm
{
``VP''和``VV NN''同时出现的次数
=
1
}}{
\textrm
{
``VP''
出现的次数
}
=
4
}$}
;
\node
[anchor=north west] (math1) at ([xshift=2em]treebank.north east)
{
$
\funp
{
P
}$
(VP
$
\to
$
VV NN)
}
;
\node
[anchor=north west] (math1part2) at ([xshift=-1em,yshift=0.2em]math1.south west)
{$
=
\frac
{
\textrm
{
“VP”和“VV NN”同时出现的次数
=
1
}}{
\textrm
{
“VP”
出现的次数
}
=
4
}$}
;
\node
[anchor=north west] (math1part3) at ([yshift=0.2em]math1part2.south west)
{$
=
\frac
{
1
}{
4
}$}
;
\node
[anchor=north west] (math2) at ([yshift=-6em]math1.north west)
{
P
(NP
$
\to
$
NN)
}
;
\node
[anchor=north west] (math2part2) at ([xshift=-1em,yshift=0.2em]math2.south west)
{$
=
\frac
{
\textrm
{
``NP''和``NN''同时出现的次数
=
2
}}{
\textrm
{
``NP''
出现的次数
}
=
3
}$}
;
\node
[anchor=north west] (math2) at ([yshift=-6em]math1.north west)
{
$
\funp
{
P
}$
(NP
$
\to
$
NN)
}
;
\node
[anchor=north west] (math2part2) at ([xshift=-1em,yshift=0.2em]math2.south west)
{$
=
\frac
{
\textrm
{
“NP”和“NN”同时出现的次数
=
2
}}{
\textrm
{
“NP”
出现的次数
}
=
3
}$}
;
\node
[anchor=north west] (math2part3) at ([yshift=0.2em]math2part2.south west)
{$
=
\frac
{
2
}{
3
}$}
;
\node
[anchor=north west] (math3) at ([yshift=-6em]math2.north west)
{
P
(IP
$
\to
$
NP NP)
}
;
\node
[anchor=north west] (math3part2) at ([xshift=-1em,yshift=0.2em]math3.south west)
{$
=
\frac
{
\textrm
{
``IP''和``NP NP''同时出现的次数
=
0
}}{
\textrm
{
``IP''
出现的次数
}
=
3
}$}
;
\node
[anchor=north west] (math3) at ([yshift=-6em]math2.north west)
{
$
\funp
{
P
}$
(IP
$
\to
$
NP NP)
}
;
\node
[anchor=north west] (math3part2) at ([xshift=-1em,yshift=0.2em]math3.south west)
{$
=
\frac
{
\textrm
{
“IP”和“NP NP”同时出现的次数
=
0
}}{
\textrm
{
“IP”
出现的次数
}
=
3
}$}
;
\node
[anchor=north west] (math3part3) at ([yshift=0.2em]math3part2.south west)
{$
=
\frac
{
0
}{
3
}$}
;
\begin{pgfonlayer}
{
background
}
...
...
Chapter3/Figures/figure-examples-of-chinese-word-segmentation-based-on-1-gram-model.tex
查看文件 @
b87c1f4e
...
...
@@ -19,7 +19,7 @@
\end{pgfonlayer}
}
\node
[anchor=west,ugreen] (P) at ([xshift=5.2em,yshift=-0.8em]corpus.east)
{
\large
{
\funp
{
P
}
(
$
\cdot
$
)
}}
;
\node
[anchor=west,ugreen] (P) at ([xshift=5.2em,yshift=-0.8em]corpus.east)
{
\large
{
$
\funp
{
P
}
(
\cdot
)
$
}}
;
\node
[anchor=south] (modellabel) at (P.north)
{{
\color
{
ublue
}
{
\scriptsize
\textbf
{
统计模型
}}}}
;
\begin{pgfonlayer}
{
background
}
...
...
@@ -41,9 +41,9 @@
{
\footnotesize
{
\node
[anchor=west] (label1) at (0,6em)
{
实际上,通过学习我们得到了一个分词模型
\funp
{
P
}
(
$
\cdot
$
)
,给定任意的分词结果
}
;
\node
[anchor=north west] (label1part2) at ([yshift=0.5em]label1.south west)
{$
W
=
w
_
1
w
_
2
...w
_
n
$
,都能通过
\funp
{
P
}
(
$
W
$
)=
$
\funp
{
P
}
(
w
_
1
)
\cdot
\funp
{
P
}
(
w
_
2
)
\cdot
...
\cdot
\funp
{
P
}
(
w
_
n
)
$
计算这种分词的
\hspace
{
0.13em
}
}
;
\node
[anchor=north west] (label1part3) at ([yshift=0.5em]label1part2.south west)
{
概率值
}
;
\node
[anchor=west] (label1) at (0,6em)
{
实际上,通过学习我们得到了一个分词模型
$
\funp
{
P
}
(
\cdot
)
$
,给定任意的分词结果
}
;
\node
[anchor=north west] (label1part2) at ([yshift=0.5em]label1.south west)
{$
W
=
w
_
1
w
_
2
...w
_
n
$
,都能通过
$
\funp
{
P
}
(
W
)=
\funp
{
P
}
(
w
_
1
)
\cdot
\funp
{
P
}
(
w
_
2
)
\cdot
...
\cdot
\funp
{
P
}
(
w
_
n
)
$
计算这种分
\hspace
{
0.13em
}
}
;
\node
[anchor=north west] (label1part3) at ([yshift=0.5em]label1part2.south west)
{
词的
概率值
}
;
}
\begin{pgfonlayer}
{
background
}
...
...
@@ -96,13 +96,13 @@
\node
[anchor=north west,minimum height=1.6em] (data33) at ([yshift=0.3em]data23.south west)
{}
;
{
\node
[anchor=north west] (data41) at (data31.south west)
{
确实/现在/数据/很多
}
;
\node
[anchor=north west] (data41) at (data31.south west)
{
确实/现在/数据/很
/
多
}
;
}
{
\node
[anchor=north west] (data42) at (data32.south west)
{$
\funp
{
P
}
(
\textrm
{
确实
}
)
\cdot
\funp
{
P
}
(
\textrm
{
现在
}
)
\cdot
\funp
{
P
}
(
\textrm
{
数据
}
)
\cdot
$}
;
}
{
\node
[anchor=north west] (data43) at ([yshift=-0.
2em,xshift=-2
em]data33.south west)
{
\color
{
red
}{
\textbf
{
输出
}}}
;
\node
[anchor=north west] (data43) at ([yshift=-0.
4em,xshift=-1.4
em]data33.south west)
{
\color
{
red
}{
\textbf
{
输出
}}}
;
\draw
[->,red,thick] (data43.west)--([xshift=-1em]data43.west);
}
{
...
...
Chapter3/Figures/figure-mt-system-as-a-black-box.tex
查看文件 @
b87c1f4e
...
...
@@ -35,7 +35,7 @@
}
{
\node
[rectangle,fill=ublue,inner sep=2pt]
[fit = (mtinputlabel) (mtoutputlabel) (inputmarking) (outputmarking)]
{{
\color
{
white
}
\textbf
{
\Large
{
MT
系统
}}}}
;
\node
[rectangle,fill=ublue,inner sep=2pt]
[fit = (mtinputlabel) (mtoutputlabel) (inputmarking) (outputmarking)]
{{
\color
{
white
}
\textbf
{
\Large
{
机器翻译
系统
}}}}
;
}
...
...
Chapter3/Figures/figure-mt=language-analysis+translation-engine.tex
查看文件 @
b87c1f4e
...
...
@@ -25,7 +25,7 @@
}
\end{scope}
\node
[anchor=west,draw,thick,inner sep=3pt,ublue] (mtengine) at ([xshift=1.0
5in]input.east)
{{
\scriptsize
MT
系统
}}
;
\node
[anchor=west,draw,thick,inner sep=3pt,ublue] (mtengine) at ([xshift=1.0
in]input.east)
{{
\scriptsize
机器翻译
系统
}}
;
\begin{scope}
[scale=0.8,xshift=3.0in,yshift=-0.87in,level distance=20pt,sibling distance=-3pt,grow'=up]
{
\scriptsize
...
...
@@ -49,8 +49,8 @@
\draw
[->,thick]
([xshift=-6pt]output.west) -- ([xshift=2pt]output.west);
{
\draw
[->,thick]
([xshift=-1
2
pt]mtengine.west) -- ([xshift=-2pt]mtengine.west);
\draw
[->,thick]
([xshift=2pt]mtengine.east) -- ([xshift=1
2
pt]mtengine.east);
\draw
[->,thick]
([xshift=-1
0
pt]mtengine.west) -- ([xshift=-2pt]mtengine.west);
\draw
[->,thick]
([xshift=2pt]mtengine.east) -- ([xshift=1
0
pt]mtengine.east);
}
{
...
...
Chapter3/Figures/figure-perspectives-of-expert-ordinary-and-syntactic-parser.tex
查看文件 @
b87c1f4e
...
...
@@ -72,9 +72,9 @@
\\
语言学家
:
&
不对
&
对
&
不对
\\
我们
:
&
似乎对了
&
比较肯定
&
不太可能
\\
分析器
:
&
$
\textrm
{
P
}
=
0
.
2
$
&
$
\textrm
{
P
}
=
0
.
6
$
&
$
\textrm
{
P
}
=
0
.
1
$
语言学家
:
&
不对
&
对
&
不对
\\
我们
:
&
似乎对了
&
比较肯定
&
不太可能
\\
分析器
:
&
$
\textrm
{
P
}
=
0
.
2
$
&
$
\textrm
{
P
}
=
0
.
6
$
&
$
\textrm
{
P
}
=
0
.
1
$
\end{tabular}
%---------------------------------------------------------------------
...
...
Chapter3/Figures/figure-probability-values-corresponding-to-different-derivations.tex
查看文件 @
b87c1f4e
...
...
@@ -76,11 +76,11 @@
\node
[] (d2) at (0em,-10em)
{$
d
_
2
$}
;
\node
[] (d3) at (8.5em,-10em)
{$
d
_
2
$}
;
\node
[anchor=east] (d1p) at ([xshift=0.4em]d1.west)
{$
\
textrm
{
P
}
(
$}
;
\node
[anchor=east] (d1p) at ([xshift=0.4em]d1.west)
{$
\
funp
{
P
}
(
$}
;
\node
[anchor=west] (d1p2) at ([xshift=-0.4em]d1.east)
{$
)=
0
.
0123
$}
;
\node
[anchor=east] (d2p) at ([xshift=0.4em]d2.west)
{$
\
textrm
{
P
}
(
$}
;
\node
[anchor=east] (d2p) at ([xshift=0.4em]d2.west)
{$
\
funp
{
P
}
(
$}
;
\node
[anchor=west] (d2p2) at ([xshift=-0.4em]d2.east)
{$
)=
0
.
4031
$}
;
\node
[anchor=east] (d3p) at ([xshift=0.4em]d3.west)
{$
\
textrm
{
P
}
(
$}
;
\node
[anchor=east] (d3p) at ([xshift=0.4em]d3.west)
{$
\
funp
{
P
}
(
$}
;
\node
[anchor=west] (d3p2) at ([xshift=-0.4em]d3.east)
{$
)=
0
.
0056
$}
;
\end{tikzpicture}
...
...
Chapter3/Figures/figure-process-of-statistical-syntax-analysis.tex
查看文件 @
b87c1f4e
...
...
@@ -46,7 +46,7 @@
\end{pgfonlayer}
}
\node
[anchor=west,ugreen] (P) at ([xshift=5.95em,yshift=-0.8em]corpus.east)
{
\large
{
P(
$
\cdot
$
)
}}
;
\node
[anchor=west,ugreen] (P) at ([xshift=5.95em,yshift=-0.8em]corpus.east)
{
\large
{
$
P
(
\cdot
)
$
}}
;
\node
[anchor=south] (modellabel) at (P.north)
{{
\color
{
ublue
}
{
\scriptsize
\textbf
{
统计分析模型
}}}}
;
\begin{pgfonlayer}
{
background
}
...
...
Chapter3/Figures/figure-transition-prob-and-launch-prob-in-coin-toss-game.tex
查看文件 @
b87c1f4e
...
...
@@ -52,7 +52,7 @@
\draw
[thick]
(o.north west) -- (o.south east);
\node
[anchor=south west]
at ([yshift=-1em,xshift=-1.4em]o.45)
{
\tiny
{
可见
}}
;
\node
[anchor=north east]
at ([yshift=1em,xshift=1em]o.-135)
{
\tiny
{
隐
藏
}}
;
\node
[anchor=north east]
at ([yshift=1em,xshift=1em]o.-135)
{
\tiny
{
隐
含
}}
;
\begin{pgfonlayer}
{
background
}
\node
[rectangle,inner sep=0.5em,rounded corners=2pt,fill=red!10] [fit = (o)(n32)(rc)(cb) ] (box1)
{}
;
...
...
Chapter3/Figures/figure-word-segmentation-based-on-statistics.tex
查看文件 @
b87c1f4e
...
...
@@ -29,7 +29,7 @@
}
{
\node
[anchor=west,ugreen] (P) at ([xshift=5.2em,yshift=-0.8em]corpus.east)
{
\large
{
\funp
{
P
}
(
$
\cdot
$
)
}}
;
\node
[anchor=west,ugreen] (P) at ([xshift=5.2em,yshift=-0.8em]corpus.east)
{
{$
\funp
{
P
}
(
\cdot
)
$
}}
;
\node
[anchor=south] (modellabel) at (P.north)
{{
\color
{
ublue
}
{
\scriptsize
\textbf
{
统计模型
}}}}
;
}
...
...
@@ -59,16 +59,16 @@
}
{
\node
[anchor=north west] (seg4) at ([xshift=-1.0em,yshift=0.4em]seg3.south west)
{
...
}
;
\node
[anchor=east,ugreen] (p1seg1) at ([xshift=0.5em]seg1.west)
{
P(
}
;
\node
[anchor=east,ugreen] (p1seg1) at ([xshift=0.5em]seg1.west)
{
$
\funp
{
P
}
(
$
}
;
\node
[anchor=west,ugreen] (p2seg1) at ([xshift=-0.5em]seg1.east)
{
)=0.1
}
;
\node
[anchor=east,ugreen] (p1seg2) at ([xshift=0.5em]seg2.west)
{
P(
}
;
\node
[anchor=east,ugreen] (p1seg2) at ([xshift=0.5em]seg2.west)
{
$
\funp
{
P
}
(
$
}
;
\node
[anchor=west,ugreen] (p2seg2) at ([xshift=-0.5em]seg2.east)
{
)=0.6
}
;
\node
[anchor=east,ugreen] (p1seg3) at ([xshift=0.5em]seg3.west)
{
P(
}
;
\node
[anchor=east,ugreen] (p1seg3) at ([xshift=0.5em]seg3.west)
{
$
\funp
{
P
}
(
$
}
;
\node
[anchor=west,ugreen] (p2seg3) at ([xshift=-0.5em]seg3.east)
{
)=0.2
}
;
}
{
\node
[anchor=east,draw,dashed,red,thick,minimum width=13em,minimum height=1.4em] (final) at (p2seg2.east)
{}
;
\node
[anchor=east,draw,dashed,red,thick,minimum width=13
.2
em,minimum height=1.4em] (final) at (p2seg2.east)
{}
;
\node
[anchor=west,red] (finallabel) at ([xshift=3.1em]sentlabel.east)
{
输出概率最大的结果
}
;
%\node [anchor=north east,red] (finallabel2) at ([yshift=0.5em]finallabel.south east) {的结果};
\draw
[->,thick,red] ([xshift=0.0em,yshift=-0.5em]final.north east) ..controls +(east:0.2) and +(south:1.0).. ([xshift=2.0em]finallabel.south);
...
...
Chapter3/chapter3.aux
0 → 100644
查看文件 @
b87c1f4e
差异被折叠。
点击展开。
Chapter3/chapter3.tex
查看文件 @
b87c1f4e
This source diff could not be displayed because it is too large. You can
view the blob
instead.
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