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
137e91bd
Commit
137e91bd
authored
Jan 06, 2021
by
曹润柘
Browse files
Options
Browse Files
Download
Plain Diff
合并分支 'master' 到 'caorunzhe'
Master 查看合并请求
!798
parents
aae321d4
cb9e76ab
全部展开
隐藏空白字符变更
内嵌
并排
正在显示
7 个修改的文件
包含
20 行增加
和
17 行删除
+20
-17
Chapter14/Figures/figure-different-integration-model.tex
+1
-1
Chapter14/Figures/figure-iteration.tex
+10
-10
Chapter14/Figures/figure-mask-predict.tex
+5
-2
Chapter14/Figures/figure-reranking.tex
+1
-1
Chapter14/Figures/figure-word-string-representation.tex
+2
-2
Chapter14/chapter14.tex
+0
-0
Chapter17/chapter17.tex
+1
-1
没有找到文件。
Chapter14/Figures/figure-different-integration-model.tex
查看文件 @
137e91bd
...
...
@@ -98,7 +98,7 @@
\draw
[-latex,blue] (lattice5) to [out=-60,in=-90] (lattice3);
\begin{pgfonlayer}
{
background
}
\node
[draw=blue,fill=white,drop shadow,thick,rounded corners=3pt,inner sep=5pt,fit=(lattice1) (lattice2) (lattice3) (lattice4) (lattice5),label=
{
[font=
\tiny
,label distance=0pt]90:
Lattice
}
] (lattice)
{}
;
\node
[draw=blue,fill=white,drop shadow,thick,rounded corners=3pt,inner sep=5pt,fit=(lattice1) (lattice2) (lattice3) (lattice4) (lattice5),label=
{
[font=
\tiny
,label distance=0pt]90:
词格
}
] (lattice)
{}
;
\end{pgfonlayer}
\draw
[->,very thick] (output) to (lattice);
...
...
Chapter14/Figures/figure-iteration.tex
查看文件 @
137e91bd
...
...
@@ -11,29 +11,29 @@
\node
(point)[right of=decoder
_
2,xshift=2.5cm,]
{
\LARGE
{
...
}}
;
\node
(decoder
_
3)[er,thick,draw,right of=point,xshift=2.5cm,fill=red!20]
{
\Large
{
解码器
}}
;
\draw
[->,very thick,draw=black!70]([xshift=0.2cm]encoder.east) -- ([xshift=-0.2cm]decoder
_
1.west);
\draw
[->,very thick,draw=black!70]([xshift=0.2cm]decoder
_
1.east) -- ([xshift=-0.2cm]decoder
_
2.west);
\draw
[->,very thick,draw=black!70]([xshift=0.2cm]decoder
_
2.east) -- ([xshift=-0.1cm]point.west);
\draw
[->,very thick,draw=black!70]([xshift=0.1cm]point.east) -- ([xshift=-0.2cm]decoder
_
3.west);
%
\draw [->,very thick,draw=black!70]([xshift=0.2cm]decoder_1.east) -- ([xshift=-0.2cm]decoder_2.west);
%
\draw [->,very thick,draw=black!70]([xshift=0.2cm]decoder_2.east) -- ([xshift=-0.1cm]point.west);
%
\draw [->,very thick,draw=black!70]([xshift=0.1cm]point.east) -- ([xshift=-0.2cm]decoder_3.west);
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=-1cm]encoder.south) -- ([xshift=0,yshift=-0.2cm]encoder.south);
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=0.2cm]encoder.north) -- ([xshift=0,yshift=1cm]encoder.north);
\node
[below of = encoder,xshift=0cm,yshift=2.2cm]
{
预测目标长度
}
;
\node
[below of = encoder,xshift=0cm,yshift=-2.2cm]
{
\Large
$
x
$}
;
\node
[below of = encoder,xshift=0cm,yshift=-2.2cm]
{
\Large
$
\seq
{
x
}
$}
;
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=-1cm]decoder
_
1.south) -- ([xshift=0,yshift=-0.2cm]decoder
_
1.south);
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=0.2cm]decoder
_
1.north) -- ([xshift=0,yshift=1cm]decoder
_
1.north);
\node
[below of = decoder
_
1,xshift=0cm,yshift=-2.2cm]
{
\Large
$
x'
$}
;
\node
(line1
_
1)[below of = decoder
_
1,xshift=0cm,yshift=2.2cm]
{
\Large
$
y'
$}
;
\node
[below of = decoder
_
1,xshift=0cm,yshift=-2.2cm]
{
\Large
$
\seq
{
x'
}
$}
;
\node
(line1
_
1)[below of = decoder
_
1,xshift=0cm,yshift=2.2cm]
{
\Large
$
\seq
{
y
}^{
[
1
]
}
$}
;
\draw
[->,thick,]([xshift=0,yshift=-1cm]decoder
_
2.south) -- ([xshift=0,yshift=-0.2cm]decoder
_
2.south);
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=0.2cm]decoder
_
2.north) -- ([xshift=0,yshift=1cm]decoder
_
2.north);
\node
(line1
_
2)[below of = decoder
_
2,xshift=0cm,yshift=-2.2cm]
{
\Large
$
y'
$}
;
\node
[below of = decoder
_
2,xshift=0cm,yshift=2.2cm]
{
\Large
$
y''
$}
;
\node
(line1
_
2)[below of = decoder
_
2,xshift=0cm,yshift=-2.2cm]
{
\Large
$
\seq
{
y
}^{
[
1
]
}
$}
;
\node
[below of = decoder
_
2,xshift=0cm,yshift=2.2cm]
{
\Large
$
\seq
{
y
}^{
[
2
]
}
$}
;
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=-1cm]decoder
_
3.south) -- ([xshift=0,yshift=-0.2cm]decoder
_
3.south);
\draw
[->,very thick,draw=black!70]([xshift=0,yshift=0.2cm]decoder
_
3.north) -- ([xshift=0,yshift=1cm]decoder
_
3.north);
\node
(line3
_
2)[below of = decoder
_
3,xshift=0cm,yshift=-2.2cm]
{
\Large
$
y
^{
N
-
1
}$}
;
\node
[below of = decoder
_
3,xshift=0cm,yshift=2.2cm]
{
\Large
$
y
^
N
$}
;
\node
(line3
_
2)[below of = decoder
_
3,xshift=0cm,yshift=-2.2cm]
{
\Large
$
\seq
{
y
}^{
[
N
-
1
]
}$}
;
\node
[below of = decoder
_
3,xshift=0cm,yshift=2.2cm]
{
\Large
$
\seq
{
y
}^{
[
N
]
}
$}
;
\draw
[->,very thick,draw=black!70, out=0, in=180,dotted]
(line1
_
1.east) to (line1
_
2.west);
\draw
[->,very thick,draw=black!70, out=0, in=180,dotted]
([xshift=4cm]line1
_
1.east) to ([xshift=3cm]line1
_
2.west);
...
...
Chapter14/Figures/figure-mask-predict.tex
查看文件 @
137e91bd
...
...
@@ -5,8 +5,11 @@
\node
(encoder)[er,thick,minimum width=5.5cm,fill=ugreen!20]
{
\huge
{
编码器
}}
;
\node
(decoder)[er,thick,right of=encoder,xshift=7.75cm,fill=red!20]
{
\huge
{
解码器
}}
;
\node
(decoder
_
1)[er,thick,right of=decoder,xshift=8.75cm,fill=red!20]
{
\huge
{
解码器
}}
;
\draw
[->,very thick,draw=black!70]([xshift=0.2cm]encoder.east) -- ([xshift=-0.2cm]decoder.west);
\draw
[->,very thick,draw=black!70]([xshift=0.2cm]decoder.east) -- ([xshift=-0.2cm]decoder
_
1.west);
\draw
[->,very thick,draw=blue!70]([xshift=0.2cm]encoder.east) -- ([xshift=-0.2cm]decoder.west);
\begin{pgfonlayer}
{
background
}
\draw
[->,very thick,draw=blue!70]([xshift=0.2cm,yshift=-0.8em]encoder.east) -- ([xshift=-0.2cm,yshift=-0.8em]decoder
_
1.west);
\end{pgfonlayer}
\foreach
\x
in
{
-2.2cm,-1.1cm,...,2.2cm
}
\draw
[->,very thick,draw=black!70]([xshift=
\x
,yshift=-1cm]encoder.south) -- ([xshift=
\x
,yshift=-0.2cm]encoder.south);
...
...
Chapter14/Figures/figure-reranking.tex
查看文件 @
137e91bd
...
...
@@ -34,7 +34,7 @@
\node
[anchor=south,font=\scriptsize,align=center]
(w5) at ([yshift=1.6em]box3.north)
{
\tiny\bfnew
{
对
\
这个
\
问题
\
存在
\
不同的
\
看法
}}
;
\node
[font=\tiny]
at ([xshift=-0.8em,yshift=-0.6em]encoder.east)
{$
N
\times
$}
;
\node
[font=\tiny]
at ([xshift=-0.8em,yshift=-0.6em]decoder.east)
{$
1
\times
$}
;
\node
[font=\tiny]
at ([xshift=-1em,yshift=-0.6em]decoder2.east)
{$
N
$
-1
$
\times
$}
;
\node
[font=\tiny]
at ([xshift=-1em,yshift=-0.6em]decoder2.east)
{$
N
-
1
\times
$}
;
\draw
[line]
(w1.north) -- (box1.south);
\draw
[line]
(w2.north) -- (box2.south);
...
...
Chapter14/Figures/figure-word-string-representation.tex
查看文件 @
137e91bd
...
...
@@ -29,7 +29,7 @@
\node
[anchor= west] (word3) at ([xshift=1.4em,yshift=-3em]pos4.east)
{
She
}
;
\node
[anchor= west] (word4) at ([xshift=1.1em,yshift=2.8em]pos5.east)
{
Have
}
;
\node
[anchor= west] (word5) at ([xshift=1.3em,yshift=-2.8em]pos5.east)
{
Has
}
;
\node
[anchor= south] (labelb) at ([xshift=3em,yshift=-3em]word3.south)
{
\small
{
(b)
Lattice
词串表示
}}
;
\node
[anchor= south] (labelb) at ([xshift=3em,yshift=-3em]word3.south)
{
\small
{
(b)
基于词格的
词串表示
}}
;
\begin{pgfonlayer}
{
background
}
{
% I
...
...
@@ -56,7 +56,7 @@
\node
[anchor= west] (pos3) at ([xshift=3.0em]pos2.east)
{$
\circ
$}
;
\node
[anchor= west] (pos2-2) at ([xshift=0.1em,yshift=1.0em]pos2.east)
{
has
}
;
\draw
[->,thick]
(pos2.east)--(pos3.west);
\node
[anchor= south] (labela) at ([xshift=2em,yshift=-3em]pos1-2.south)
{
\small
{
(a)
$
n
$
-best词串表示
}}
;
\node
[anchor= south] (labela) at ([xshift=2em,yshift=-3em]pos1-2.south)
{
\small
{
(a)
$
n
$
-best词串表示
}}
;
\end{scope}
\end{tikzpicture}
...
...
Chapter14/chapter14.tex
查看文件 @
137e91bd
差异被折叠。
点击展开。
Chapter17/chapter17.tex
查看文件 @
137e91bd
...
...
@@ -134,7 +134,7 @@
\subsubsection
{
2. 语音识别结果的表示
}
\parinterval
级联语音翻译模型利用翻译模型将语音识别结果翻译为目标语言文本,但存在的一个问题是语音识别模型只输出One-best,其中可能存在一些识别错误,这些错误在翻译过程中会被放大,导致最终翻译结果偏离原本意思,也就是错误传播问题。传统级联语音模型的一个主要方向是丰富语音识别模型的预测结果,为翻译模型提供更多的信息,具体做法是在语音识别模型中,声学模型解码得到
{
\small\bfnew
{
词格
}}
\index
{
词格
}
(Word Lattice)
\index
{
Word Lattice
}
来取代One-best识别结果。词格是一种有向无环图,包含单个起点和终点,图中的每条边记录了每个词和对应的转移概率信息,如图
\ref
{
fig:17-6
}
所示。
\parinterval
级联语音翻译模型利用翻译模型将语音识别结果翻译为目标语言文本,但存在的一个问题是语音识别模型只输出One-best,其中可能存在一些识别错误,这些错误在翻译过程中会被放大,导致最终翻译结果偏离原本意思,也就是错误传播问题。传统级联语音模型的一个主要方向是丰富语音识别模型的预测结果,为翻译模型提供更多的信息,具体做法是在语音识别模型中,声学模型解码得到
词格
来取代One-best识别结果。词格是一种有向无环图,包含单个起点和终点,图中的每条边记录了每个词和对应的转移概率信息,如图
\ref
{
fig:17-6
}
所示。
%----------------------------------------------------------------------------------------------------
\begin{figure}
[htp]
...
...
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