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
bff00b80
Commit
bff00b80
authored
May 03, 2020
by
曹润柘
Browse files
Options
Browse Files
Download
Plain Diff
合并分支 'caorunzhe' 到 'master'
Caorunzhe 查看合并请求
!37
parents
4aeb846b
ad5bed97
隐藏空白字符变更
内嵌
并排
正在显示
5 个修改的文件
包含
50 行增加
和
20 行删除
+50
-20
Book/Chapter7/Chapter7.tex
+1
-1
Book/Chapter7/Figures/figure-batch-generation-method.tex
+14
-13
Book/Chapter7/Figures/figure-main-module.tex
+3
-1
Book/Chapter7/Figures/figure-randomly-generation-vs-generate-by-sentence-length.tex
+5
-5
Book/bibliography.bib
+27
-0
没有找到文件。
Book/Chapter7/Chapter7.tex
查看文件 @
bff00b80
...
...
@@ -946,7 +946,7 @@ y_{j}^{ls}=(1-\alpha) \cdot \tilde{y}_j + \alpha \cdot q
\vspace
{
0.3em
}
\item
需要大量自生成数据的情况。比如,需要利用机器翻译生成大量的伪数据的情况。在无指导神经机器翻译训练中,数据的生成也非常频繁。
\vspace
{
0.3em
}
\item
交互式翻译。机器翻译的一个应用场景就是交互式机器翻译
(
{
\red
参考文献!2-3篇,Guoping Huang
}
)
,即机器翻译会根据用户的行为实时进行调整,这时机器翻译的延时会影响用户体验。
\item
交互式翻译。机器翻译的一个应用场景就是交互式机器翻译
\cite
{
Domingo2017Segment
}
\cite
{
Alvaro2017Interactive
}
\cite
{
Nepveu2004Adaptive
}
,即机器翻译会根据用户的行为实时进行调整,这时机器翻译的延时会影响用户体验。
\vspace
{
0.3em
}
\item
互联网机器翻译服务和产品。在大并发时如何保证翻译的低延时也是开发这类应用中必须要考虑的。
\vspace
{
0.3em
}
...
...
Book/Chapter7/Figures/figure-batch-generation-method.tex
查看文件 @
bff00b80
\begin{tikzpicture}
\tikzstyle
{
node
}
= [minimum height=
0.8
em,draw=teal,fill=teal!10]
\tikzstyle
{
legend
}
= [minimum height=
0.8em,minimum width=0.8
em,draw]
\tikzstyle
{
node2
}
= [minimum width=
0.8em,minimum height=3.3
em,draw=blue,fill=blue!10]
\tikzstyle
{
node
}
= [minimum height=
1.0
em,draw=teal,fill=teal!10]
\tikzstyle
{
legend
}
= [minimum height=
1.0em,minimum width=1.0
em,draw]
\tikzstyle
{
node2
}
= [minimum width=
1.0em,minimum height=4.1
em,draw=blue,fill=blue!10]
\node
[node,minimum width=2.8em]
(node1) at (0,0)
{}
;
\node
[node,minimum width=4.0em,anchor=north west]
(node2) at (node1.south west)
{}
;
\node
[node,minimum width=3.2em,anchor=north west]
(node3) at (node2.south west)
{}
;
...
...
@@ -17,9 +17,9 @@
\node
[font=\scriptsize,anchor=east]
(line3) at (node3.west)
{
gpu3
}
;
\node
[font=\scriptsize,anchor=east]
(line4) at (node4.west)
{
gpu4
}
;
\node
[node2,anchor = north west]
(grad2) at ([xshift=0.3em]node5.north east)
{}
;
\draw
[->]
(-1.4em,-
2.92em) -- (9em,-2.9
2em);
\draw
[->]
(-1.4em,-
3.62em) -- (9.5em,-3.6
2em);
\node
[node,minimum width=2.8em]
(node9) at (1
3
em,0)
{}
;
\node
[node,minimum width=2.8em]
(node9) at (1
5
em,0)
{}
;
\node
[node,minimum width=4.0em,anchor=north west]
(node10) at (node9.south west)
{}
;
\node
[node,minimum width=3.2em,anchor=north west]
(node11) at (node10.south west)
{}
;
\node
[node,minimum width=3.0em,anchor=north west]
(node12) at (node11.south west)
{}
;
...
...
@@ -33,22 +33,22 @@
\node
[font=\scriptsize,anchor=east]
(line2) at (node10.west)
{
gpu2
}
;
\node
[font=\scriptsize,anchor=east]
(line3) at (node11.west)
{
gpu3
}
;
\node
[font=\scriptsize,anchor=east]
(line4) at (node12.west)
{
gpu4
}
;
\draw
[->]
(1
1.6em,-2.92em) -- (20.2em,-2.9
2em);
\draw
[->]
(1
3.6em,-3.62em) -- (22.2em,-3.6
2em);
\begin{pgfonlayer}
{
background
}
\node
[rectangle,inner sep=-0.0em,draw] [fit = (node1) (node2) (node3) (node4)] (box1)
{}
;
\node
[rectangle,inner sep=-0.0em,draw] [fit = (node5) (node6) (node7) (node8)] (box2)
{}
;
\node
[rectangle,inner sep=-0.0em,draw] [fit = (node9) (node13) (node12) (node16)] (box2)
{}
;
\end{pgfonlayer}
\node
[font=\
tiny
,anchor=north]
(legend1) at ([xshift=3em]node4.south)
{
一步一更新
}
;
\node
[font=\
tiny
,anchor=north]
(legend2) at ([xshift=2.5em]node12.south)
{
累积两步更新
}
;
\node
[font=\
tiny
,anchor=north]
(time1) at (grad2.south)
{
time
}
;
\node
[font=\
tiny
,anchor=north]
(time1) at (grad3.south)
{
time
}
;
\node
[font=\
scriptsize
,anchor=north]
(legend1) at ([xshift=3em]node4.south)
{
一步一更新
}
;
\node
[font=\
scriptsize
,anchor=north]
(legend2) at ([xshift=2.5em]node12.south)
{
累积两步更新
}
;
\node
[font=\
scriptsize
,anchor=north]
(time1) at (grad2.south)
{
time
}
;
\node
[font=\
scriptsize
,anchor=north]
(time1) at (grad3.south)
{
time
}
;
\node
[legend]
(legend3) at (2em,2em)
{}
;
\node
[font=\
tiny
,anchor=west]
(idle) at (legend3.east)
{
:空闲
}
;
\node
[font=\
scriptsize
,anchor=west]
(idle) at (legend3.east)
{
:空闲
}
;
\node
[legend,anchor=west,draw=teal,fill=teal!10]
(legend4) at ([xshift = 2em]idle.east)
{}
;
\node
[font=\
tiny
,anchor=west]
(FB) at (legend4.east)
{
:前向/反向
}
;
\node
[font=\
scriptsize
,anchor=west]
(FB) at (legend4.east)
{
:前向/反向
}
;
\node
[legend,anchor=west,draw=blue,fill=blue!10]
(legend5) at ([xshift = 2em]FB.east)
{}
;
\node
[font=\
tiny
,anchor=west]
(grad
_
sync) at (legend5.east)
{
:梯度更新
}
;
\node
[font=\
scriptsize
,anchor=west]
(grad
_
sync) at (legend5.east)
{
:梯度更新
}
;
\end{tikzpicture}
\ No newline at end of file
Book/Chapter7/Figures/figure-main-module.tex
查看文件 @
bff00b80
\begin{tikzpicture}
%左
\node
[anchor=west,draw=black,very thick,minimum width=6em,minimum height=3.5em,fill=blue!15,align=center,text=black] (part1) at (0,0)
{
\scriptsize
{
预测模块
}
\\
\tiny
{
(RNN/Transsformer)
}}
;
\node
[anchor=south] (text) at ([xshift=0.5em,yshift=-3.5em]part1.south)
{
\scriptsize
{
源语言句子(编码)
}}
;
\node
[anchor=east,draw=black,very thick,minimum width=6em,minimum height=3.5em,fill=blue!15,align=center,text=black] (part2) at ([xshift=10em]part1.east)
{
\scriptsize
{
搜索模块
}}
;
\node
[anchor=south] (text1) at ([xshift=0.5em,yshift=2.2em]part1.north)
{
\scriptsize
{
已经生成的目标语单词
}}
;
\node
[anchor=south] (text2) at ([xshift=0.5em,yshift=2.2em]part2.north)
{
\scriptsize
{
预测当前位置的单词分布
}}
;
\draw
[->,draw=black, thick] ([yshift=2em]part1.north) -- ([yshift=0.1em]part1.north);
\draw
[->,draw=black, thick] ([yshift=-2em]part1.south) -- ([yshift=-0.1em]part1.south);
\draw
[->,draw=black, thick] ([yshift=0em]part2.north) -- ([yshift=2em]part2.north);
...
...
Book/Chapter7/Figures/figure-randomly-generation-vs-generate-by-sentence-length.tex
查看文件 @
bff00b80
\begin{tikzpicture}
\tikzstyle
{
node
}
= [minimum height=
0.8
em,draw=teal,fill=teal!10]
\tikzstyle
{
node
}
= [minimum height=
1.0
em,draw=teal,fill=teal!10]
\node
[node,minimum width=2.0em]
(sent1) at (0,0)
{}
;
\node
[node,minimum width=5.0em,anchor=north west]
(sent2) at (sent1.south west)
{}
;
\node
[node,minimum width=1.0em,anchor=north west]
(sent3) at (sent2.south west)
{}
;
...
...
@@ -10,8 +10,7 @@
\node
[node,minimum width=4.5em,anchor=north west]
(sent6) at (sent5.south west)
{}
;
\node
[node,minimum width=4.5em,anchor=north west]
(sent7) at (sent6.south west)
{}
;
\node
[node,minimum width=5em,anchor=north west]
(sent8) at (sent7.south west)
{}
;
%\node[node,minimum width=2.0em] (sent3) at (0,0) {};
%\node[node,minimum width=2.0em] (sent4) at (0,0) {};
\node
[font=\scriptsize,anchor=east]
(line1) at (sent1.west)
{
sent1
}
;
\node
[font=\scriptsize,anchor=east]
(line2) at (sent2.west)
{
sent2
}
;
\node
[font=\scriptsize,anchor=east]
(line3) at (sent3.west)
{
sent3
}
;
...
...
@@ -25,7 +24,7 @@
\node
[rectangle,inner sep=-0.0em,draw] [fit = (sent1) (sent2) (sent3) (sent4)] (box1)
{}
;
\node
[rectangle,inner sep=-0.0em,draw] [fit = (sent5) (sent6) (sent7) (sent8)] (box2)
{}
;
\end{pgfonlayer}
\node
[font=\scriptsize
,anchor=west]
(node1) at ([yshift=-3.2em]sent1
.south)
{
随机生成
}
;
\node
[font=\scriptsize
,anchor=west]
(node2) at ([xshift=7.5em]node1.east
)
{
排序生成
}
;
\node
[font=\scriptsize
]
(node1) at ([yshift=-3em]sent2
.south)
{
随机生成
}
;
\node
[font=\scriptsize
]
(node2) at ([yshift=-1em]sent8.south
)
{
排序生成
}
;
\end{tikzpicture}
\ No newline at end of file
Book/bibliography.bib
查看文件 @
bff00b80
...
...
@@ -6320,3 +6320,29 @@ year = {2020},
//biburl = {https://dblp.org/rec/conf/eacl/GispertBHS17.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Domingo2017Segment,
title={Segment-based interactive-predictive machine translation},
author={Domingo, Miguel and álvaro Peris and Casacuberta, Francisco},
journal={Machine Translation},
volume={31},
number={4},
pages={163-185},
year={2017},
}
@article{Alvaro2017Interactive,
title={Interactive neural machine translation},
author={Alvaro Peris and Domingo, Miguel and Casacuberta, Francisco},
journal={Computer Speech & Language},
volume={45},
number={Sep.},
pages={201-220},
year={2017},
}
@inproceedings{Nepveu2004Adaptive,
title={Adaptive Language and Translation Models for Interactive Machine Translation},
author={Nepveu, Laurent and Lapalme, Guy and Langlais, Philippe and Foster, George F.},
booktitle={Conference on Empirical Methods in Natural Language Processing},
year={2004},
}
\ No newline at end of file
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