Skip to content

M
mtbookv2
Commit 3f1c3127 by 曹润柘
Options

合并分支 'caorunzhe' 到 'master' 

Caorunzhe

查看合并请求 !577
parents 98bf9ea2 2c9cc68c
正在显示 包含 420 行增加 和 0 行删除
Chapter18/Figures/figure-comparison-of-incremental-model-optimization-methods.tex 0 → 100644
\begin{tabular}{c c c}
\begin{tikzpicture}
\begin{scope}
% ,minimum height =1em,minimum width=2em
\tikzstyle{model} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=blue!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{data} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=green!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{word} = [inner sep=3.5pt,font=\footnotesize]
\node[data] (old) at (0,0) {旧数据};
\node[data] (new) at ([xshift=3em]old.east) {新数据};
\node[data] (all) at ([xshift=2.55em,yshift=-4em]old.south) {最终数据};
\node[model] (final_model) at ([xshift=0em,yshift=-4em]all.south) {最终模型};
\draw [->,thick] ([yshift=-0.2em]old.south) .. controls +(south:2.5em) and +(north:2.5em) .. ([xshift=-0.2em,yshift=0.2em]all.north);
\draw [->,thick] ([yshift=-0.2em]new.south) .. controls +(south:2.5em) and +(north:2.5em) .. ([xshift=0.2em,yshift=0.2em]all.north);
\draw [->,thick] ([yshift=-0.2em]all.south) -- ([yshift=0.2em]final_model.north)node[pos=0.5,right,align=center,font=\footnotesize] {训练};
\node[word] at ([yshift=-2em]final_model.south){（a）数据混合};
\end{scope}
\end{tikzpicture}
&
\begin{tikzpicture}
\begin{scope}
\tikzstyle{model} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=blue!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{data} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=green!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{word} = [inner sep=3.5pt,font=\footnotesize]
\node[data] (old) at (0,0) {旧数据};
\node[data] (new) at ([xshift=3em]old.east) {新数据};
\node[model] (old_model) at ([yshift=-4em]old.south) {旧模型};
\node[model] (new_model) at ([yshift=-4em]new.south) {新模型};
\node[model] (final_model) at ([xshift=2.55em,yshift=-4em]old_model.south) {最终模型};
\draw [->,thick] ([yshift=-0.2em]old.south) -- ([yshift=0.2em]old_model.north) node[pos=0.5,left,align=center,font=\footnotesize] {训练};
\draw [->,thick] ([yshift=-0.2em]new.south) -- ([yshift=0.2em]new_model.north) node[pos=0.5,right,align=center,font=\footnotesize] {训练};
\draw [->,thick] ([yshift=-0.2em]old_model.south) .. controls +(south:2.5em) and +(north:2.5em) .. ([xshift=-0.2em,yshift=0.2em]final_model.north);
\draw [->,thick] ([yshift=-0.2em]new_model.south) .. controls +(south:2.5em) and +(north:2.5em) .. ([xshift=0.2em,yshift=0.2em]final_model.north);
\node[word] at ([yshift=2em]final_model.north) {插值};
\node[word] at ([yshift=-2em]final_model.south){（b）模型插值};
%空白占位
\node[word] at ([xshift=-3em]old.west) {};
\node[word] at ([xshift=3em]new.east) {};
\end{scope}
\end{tikzpicture}
&
\begin{tikzpicture}
\begin{scope}
\tikzstyle{model} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=blue!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{data} = [draw,black,very thick,inner sep=3.5pt,rounded corners=4pt,fill=green!20,minimum width=4em,minimum height=1.5em,font=\footnotesize]
\tikzstyle{word} = [inner sep=3.5pt,font=\footnotesize]
\node[data] (old) at (0,0) {旧数据};
\node[data] (new) at ([xshift=3em]old.east) {新数据};
\node[model] (final_model) at ([yshift=-8.8em]new.south) {最终模型};
\draw [->,thick] ([yshift=-0.2em]new.south) -- ([xshift=0.2em,yshift=0.2em]final_model.north) node[pos=0.5,right,align=center,font=\footnotesize] {目标\\函数1};
\draw [->,thick,dashed] ([yshift=-0.2em]old.south) .. controls +(south:4.5em) and +(north:4.5em) .. ([xshift=-0.2em,yshift=0.2em]final_model.north) node[align=center,font=\footnotesize] at ([xshift=-0.1em,yshift=-4em]old.south) {目标\\函数2};
\node[word] at ([yshift=-2em,xshift=-2.55em]final_model.south){（c）多目标训练};
\end{scope}
\end{tikzpicture}
\end{tabular}
\ No newline at end of file
Chapter18/Figures/figure-memory-multi-use.tex 0 → 100644
\begin{tabular}{c c}
\begin{tikzpicture}
\begin{scope}
% ,minimum height =1em,minimum width=2em
\tikzstyle{memory} = [draw,black,very thick,inner sep=2pt,rounded corners=0pt,fill=blue!20,minimum width=2em,minimum height=1.5em,anchor=west]
\tikzstyle{thread} = [very thick,inner sep=3.5pt,rounded corners=0pt,minimum width=3em,minimum height=1.5em]
\tikzstyle{word} = [inner sep=3.5pt,font=\scriptsize]
\node[thread] (one) at (0,0) {};
\node [word] at (one.north) {\scriptsize 数据1};
\draw[|-|,very thick] (-1.5em,0em) -- (1.6em,0em);
\node[thread,minimum width=5em] (two) at ([yshift=-1em,xshift=2.6em]one.south east) {};
\node [word] at (two.north) {\scriptsize 数据2};
\draw[|-|,very thick] (1.8em,-1.8em) -- (6.5em,-1.8em);
\node[thread,minimum width=4em] (three) at ([yshift=-1em,xshift=0.3em]two.south east) {};
\node [word] at (three.north) {\scriptsize 数据3};
\draw[|-|,very thick] (5em,-1.8*2em) -- (9em,-1.8*2em);
\node[thread,minimum width=2em] (four) at ([yshift=-1em,xshift=1.2em]three.south east) {};
\node [word] at (four.north) {\scriptsize 数据4};
\draw[|-|,very thick] (9.3em,-1.8*3em) -- (11em,-1.8*3em);
\node [memory] (mone) at ([yshift=4em,xshift=1em]one.north) {};
\node [memory] (mtwo) at ([xshift=0em]mone.east) {};
\node [memory] (mthree) at ([xshift=0em]mtwo.east) {};
\node [memory] (mfour) at ([xshift=0em]mthree.east) {};
\draw[->,very thick] (-0.8,-2.5) -- (4.7,-2.5);
\draw[->,very thick] (-0.8,-2.5) -- (-0.8,1);
\node [word] (time) at ([yshift=-1.5em,xshift=0.3em]four.south) {\scriptsize 时间线};
\node [word] (time) at ([yshift=1.5em,xshift=-2.2em]one.west) {\scriptsize 数据};
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]one.north) .. controls +(north:1.5em) and +(south:1.5em) .. ([yshift=-0.2em]mone.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]two.north) -- ([yshift=-0.2em]mtwo.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em,xshift=0.5em]three.north) .. controls +(north:3.5em) and +(south:4.5em) .. ([yshift=-0.2em]mthree.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]four.north) .. controls +(north:4.5em) and +(south:4.5em) .. ([yshift=-0.2em]mfour.south);
\node [word] at ([yshift=-6em]two.south) {（a）显存不复用};
%占位
\node[word] at ([xshift=1em]four.east) {};
\node [word] at ([xshift=1.5em,yshift=5.6em]one.north) {\scriptsize 显存};
\begin{pgfonlayer}{background}
\node [rectangle,inner sep=0.5em,rounded corners=1pt,minimum width=10em,minimum height=3.6em,fill=gray!10,drop shadow] at ([yshift=6.6em,xshift=1em]two.north) {};
\end{pgfonlayer}
\end{scope}
\end{tikzpicture}
&
\begin{tikzpicture}
\begin{scope}
%\tikzstyle{memory} = [draw,black,very thick,inner sep=2pt,rounded corners=0pt,fill=blue!20,minimum width=2em,minimum height=1.5em,anchor=west]
%\tikzstyle{thread} = [draw,black,very thick,inner sep=3.5pt,rounded corners=0pt,fill=green!20,minimum width=3em,minimum height=1.5em]
\tikzstyle{memory} = [draw,black,very thick,inner sep=2pt,rounded corners=0pt,fill=blue!20,minimum width=2em,minimum height=1.5em,anchor=west]
\tikzstyle{thread} = [very thick,inner sep=3.5pt,rounded corners=0pt,minimum width=3em,minimum height=1.5em]
\tikzstyle{word} = [inner sep=3.5pt,font=\scriptsize]
\node[thread] (one) at (0,0) {};
\node [word] at (one.north) {\scriptsize 数据1};
\draw[|-|,very thick] (-1.5em,0em) -- (1.6em,0em);
\node[thread,minimum width=5em] (two) at ([yshift=-1em,xshift=2.6em]one.south east) {};
\node [word] at (two.north) {\scriptsize 数据2};
\draw[|-|,very thick] (1.8em,-1.8em) -- (6.5em,-1.8em);
\node[thread,minimum width=4em] (three) at ([yshift=-1em,xshift=0.3em]two.south east) {};
\node [word] at (three.north) {\scriptsize 数据3};
\draw[|-|,very thick] (5em,-1.8*2em) -- (9em,-1.8*2em);
\node[thread,minimum width=2em] (four) at ([yshift=-1em,xshift=1.2em]three.south east) {};
\node [word] at (four.north) {\scriptsize 数据4};
\draw[|-|,very thick] (9.3em,-1.8*3em) -- (11em,-1.8*3em);
\node [memory] (mone) at ([yshift=4em,xshift=1em]one.north) {};
\node [memory] (mtwo) at ([xshift=0em]mone.east) {};
\node [memory,fill=white,minimum width=4em] (mthree) at ([xshift=0em]mtwo.east) {};
%\node [memory,fill=white] (mfour) at ([xshift=0em]mthree.east) {};
\draw[->,very thick] (-0.8,-2.5) -- (4.7,-2.5);
\draw[->,very thick] (-0.8,-2.5) -- (-0.8,1);
\node [word] (time) at ([yshift=-1.5em,xshift=0.3em]four.south) {\scriptsize 时间线};
\node [word] (time) at ([yshift=1.5em,xshift=-2.2em]one.west) {\scriptsize 数据};
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]one.north) .. controls +(north:1.5em) and +(south:1.5em) .. ([yshift=-0.2em,xshift=-0.4em]mone.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]two.north) .. controls +(north:3.5em) and +(south:3.5em) .. ([yshift=-0.2em,xshift=0.4em]mone.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em,xshift=0.5em]three.north) .. controls +(north:3.5em) and +(south:3.5em) .. ([yshift=-0.2em,xshift=-0.4em]mtwo.south);
\draw [->,dashed,line width=0.7pt] ([yshift=0.5em]four.north) .. controls +(north:4.5em) and +(south:3.5em) .. ([yshift=-0.2em,xshift=0.4em]mtwo.south);
\node [word] at ([xshift=1.5em,yshift=5.6em]one.north) {\scriptsize 显存};
\node [word] at ([yshift=-6em]two.south) {（b）显存复用};
\begin{pgfonlayer}{background}
\node [rectangle,inner sep=0.5em,rounded corners=1pt,minimum width=10em,minimum height=3.6em,fill=gray!10,drop shadow] at ([yshift=6.6em,xshift=1em]two.north) {};
\end{pgfonlayer}
\end{scope}
\end{tikzpicture}
\end{tabular}
\ No newline at end of file
Chapter18/Figures/figure-translation-interfered.tex 0 → 100644
%%% outline
%-------------------------------------------------------------------------
\begin{tikzpicture}[scale=0.8]
\tikzstyle{every node}=[scale=0.8]
\tikzstyle{node}=[rounded corners=4pt, draw,minimum width=3em, minimum height=2em, drop shadow={shadow xshift=0.14em, shadow yshift=-0.14em}]
\begin{scope}
%\draw[fill=yellow!20] (-5em, 0) -- (-6em, 1em) -- (5em, 1em) -- (6em, 0em) -- (5em, -1em) -- (-6em, -1em) -- (-5em, 0em);
%\draw[fill=yellow!20] (-5em, 10em) -- (-6em, 11.2em) -- (5em, 11.2em) -- (6em, 10em) -- (5em,8.8em) -- (-6em, 8.8em) -- (-5em, 10em);
\node[] (n1) at (0,0){小牛翻译的总部在哪里？};
\node[node,fill=blue!20] (c1) at (0, 5em){\scriptsize\bfnew{机器翻译}};
\node[align=left] (n2) at (0,10em){Where is the headquarters \\ of {\color{red} Mavericks Translation}?};
\node [draw,single arrow,inner ysep=0.3em, minimum height=2.4em, rotate=90,fill=cyan!40,very thin] (arrow1) at (0, 2.4em) {};
\node [draw,single arrow,inner ysep=0.3em, minimum height=2em, rotate=90,fill=cyan!40,very thin] (arrow1) at (0, 7.2em) {};
\node[font=\Large,text=red] at (0, -2em){\ding{56}};
\end{scope}
\begin{scope}[xshift=14em]
%\draw[fill=yellow!20] (-5em, 0) -- (-6em, 1em) -- (5em, 1em) -- (6em, 0em) -- (5em, -1em) -- (-6em, -1em) -- (-5em, 0em);
%\draw[fill=yellow!20] (-5em, 10em) -- (-6em, 11.2em) -- (5em, 11.2em) -- (6em, 10em) -- (5em,8.8em) -- (-6em, 8.8em) -- (-5em, 10em);
\node[] (n3) at (0,0){小牛翻译的总部在哪里？};
\node[node,fill=blue!20] (c2) at (-3em, 5em){\scriptsize\bfnew{机器翻译}};
\node[node,fill=red!20] (c3) at (3em, 5em){\scriptsize\bfnew{术语词典}};
\node[font=\scriptsize,draw,inner sep=3pt,fill=red!20,minimum height=1em] (w1) at (9em, 6.5em){小牛翻译};
\node[font=\scriptsize,draw,inner sep=3pt,fill=red!20,minimum height=1em] (w2) at (9em, 3.5em){NiuTrans};
\node[font=\Large] (add) at (0em, 5em){+};
\node[align=left] (n4) at (0,10em){Where is the headquarters \\ of {\color{red} NiuTrans}?};
\node [draw,single arrow,inner ysep=0.3em, minimum height=2.4em, rotate=90,fill=cyan!40,very thin] (arrow1) at (0, 2.4em) {};
\node [draw,single arrow,inner ysep=0.3em, minimum height=2em, rotate=90,fill=cyan!40,very thin] (arrow1) at (0, 7.2em) {};
\draw[dash pattern=on 1pt off 0.5pt,black,line width=1.2pt,->, out=180, in=45] ([xshift=-0.2em]w1.180) to ([xshift=0.2em]c3.20);
\draw[dash pattern=on 1pt off 0.5pt,black,line width=1.2pt,->,out=180,in=-45] ([xshift=-0.2em]w2.180) to ([xshift=0.2em]c3.-20);
\node[font=\Large,text=ugreen] at (0, -2em){\ding{52}};
\end{scope}
\end{tikzpicture}
bibliography.bib
......@@ -11929,6 +11929,195 @@ author = {Zhuang Liu and
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 18------------------------------------------------------
@article{DBLP:journals/corr/abs-2010-05680,
author = {Jiarui Fang and
Yang Yu and
Chengduo Zhao and
Jie Zhou},
title = {TurboTransformers: An Efficient {GPU} Serving System For Transformer
Models},
journal = {CoRR},
volume = {abs/2010.05680},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/HuangCLWMW18,
author = {Gao Huang and
Danlu Chen and
Tianhong Li and
Felix Wu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Multi-Scale Dense Networks for Resource Efficient Image Classification},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@article{DBLP:journals/corr/BolukbasiWDS17,
author = {Tolga Bolukbasi and
Joseph Wang and
Ofer Dekel and
Venkatesh Saligrama},
title = {Adaptive Neural Networks for Fast Test-Time Prediction},
journal = {CoRR},
volume = {abs/1702.07811},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WangXZ20,
author = {Qiang Wang and
Tong Xiao and
Jingbo Zhu},
title = {Training Flexible Depth Model by Multi-Task Learning for Neural Machine
Translation},
pages = {4307--4312},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/ijcai/ChenCWL20,
author = {Guanhua Chen and
Yun Chen and
Yong Wang and
Victor O. K. Li},
title = {Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation},
pages = {3587--3593},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2020}
}
@article{DBLP:journals/corr/abs-1912-00567,
author = {Tao Wang and
Shaohui Kuang and
Deyi Xiong and
Ant{\'{o}}nio Branco},
title = {Merging External Bilingual Pairs into Neural Machine Translation},
journal = {CoRR},
volume = {abs/1912.00567},
year = {2019}
}
@inproceedings{DBLP:conf/acl/DinuMFA19,
author = {Georgiana Dinu and
Prashant Mathur and
Marcello Federico and
Yaser Al-Onaizan},
title = {Training Neural Machine Translation to Apply Terminology Constraints},
pages = {3063--3068},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/SongZYLWZ19,
author = {Kai Song and
Yue Zhang and
Heng Yu and
Weihua Luo and
Kun Wang and
Min Zhang},
title = {Code-Switching for Enhancing {NMT} with Pre-Specified Translation},
pages = {449--459},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/HaslerGIB18,
author = {Eva Hasler and
Adri{\`{a}} de Gispert and
Gonzalo Iglesias and
Bill Byrne},
title = {Neural Machine Translation Decoding with Terminology Constraints},
pages = {506--512},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/ChatterjeeNTFSB17,
author = {Rajen Chatterjee and
Matteo Negri and
Marco Turchi and
Marcello Federico and
Lucia Specia and
Fr{\'{e}}d{\'{e}}ric Blain},
title = {Guiding Neural Machine Translation Decoding with External Knowledge},
pages = {157--168},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/PostV18,
author = {Matt Post and
David Vilar},
title = {Fast Lexically Constrained Decoding with Dynamic Beam Allocation for
Neural Machine Translation},
pages = {1314--1324},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/HokampL17,
author = {Chris Hokamp and
Qun Liu},
title = {Lexically Constrained Decoding for Sequence Generation Using Grid
Beam Search},
pages = {1535--1546},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/ThompsonGKDK19,
author = {Brian Thompson and
Jeremy Gwinnup and
Huda Khayrallah and
Kevin Duh and
Philipp Koehn},
title = {Overcoming Catastrophic Forgetting During Domain Adaptation of Neural
Machine Translation},
pages = {2062--2068},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/aclnmt/KhayrallahTDK18,
author = {Huda Khayrallah and
Brian Thompson and
Kevin Duh and
Philipp Koehn},
title = {Regularized Training Objective for Continued Training for Domain Adaptation
in Neural Machine Translation},
pages = {36--44},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@article{barone2017regularization,
title={Regularization techniques for fine-tuning in neural machine translation},
author={Barone, Antonio Valerio Miceli and Haddow, Barry and Germann, Ulrich and Sennrich, Rico},
journal={arXiv preprint arXiv:1707.09920},
year={2017}
}
@article{DBLP:journals/corr/ChuDK17,
author = {Chenhui Chu and
Raj Dabre and
Sadao Kurohashi},
title = {An Empirical Comparison of Simple Domain Adaptation Methods for Neural
Machine Translation},
journal = {CoRR},
volume = {abs/1701.03214},
year = {2017}
}
@inproceedings{DBLP:conf/coling/GuF20,
author = {Shuhao Gu and
Yang Feng},
title = {Investigating Catastrophic Forgetting During Continual Training for
Neural Machine Translation},
pages = {4315--4326},
publisher = {International Committee on Computational Linguistics},
year = {2020}
}
%%%%% chapter 18------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
......
Markdown 格式
0% 或
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！
请 注册 或者 后发表评论