Commit f009aeda by 单韦乔

13.1更新

parent df924ae7
\begin{tikzpicture}
\tikzstyle{node} =[font=\scriptsize]
\tikzstyle{sentence} =[font=\scriptsize,fill=blue!5!white]
\node[sentence] (node1) at (0,0) {[`low', `lower', `newest', `widest']};
\node[sentence,anchor = north] (node2) at ([yshift = -1em]node1.south) {[`l o w $<$e$>$':5, `l o w e r $<$e$>$':2, `n e w e s t $<$e$>$':6, `w i d e s t $<$e$>$':3]};
\node[sentence,anchor = north] (node3) at ([yshift = -1.5em]node2.south) {[`l o w $<$e$>$':5, `l o w e r $<$e$>$':2, `n e w {\red es} t $<$e$>$':6, `w i d {\red es} t $<$e$>$':3]};
\node[sentence,anchor = north] (node4) at ([yshift = -1em]node3.south) {[`l o w $<$e$>$':5, `l o w e r $<$e$>$':2, `n e w {\red est} $<$e$>$':6, `w i d {\red est} $<$e$>$':3]};
\node[sentence,anchor = north] (node5) at ([yshift = -1em]node4.south) {[`l o w $<$e$>$':5, `l o w e r $<$e$>$':2, `n e w {\red est$<$e$>$}':6, `w i d {\red est$<$e$>$}':3]};
\node[sentence,anchor = north] (node6) at ([yshift = -1em]node5.south) {$\cdots$};
\node[node,anchor = north] (node7) at ([yshift = -1.6em]node6.south) {直到达到预设的子词词表大小或下一个最高频的字节对出现频率为1。};
\draw[->,line width=.03cm] ([yshift=0em]node1.south) -- ([yshift=0em]node2.north);
\draw[->,line width=.03cm] ([yshift=0em]node3.south) -- ([yshift=0em]node4.north);
\draw[->,line width=.03cm] ([yshift=0em]node4.south) -- ([yshift=0em]node5.north);
\draw[->,line width=.03cm] ([yshift=0em]node5.south) -- ([yshift=0em]node6.north);
\node[node,anchor = west] (node8) at ([xshift = 2em,yshift = 2em]node7.east) {对于词表外的词lowest};
\node[node,anchor = north west] (node9) at ([yshift = 0.3em]node8.south west) {可以被分割为low est};
\node[node,font=\scriptsize,anchor = north,fill=ugreen!5,drop shadow] (dict) at ([xshift = 8em,yshift = -5em]node6.south){\begin{tabular}{llllll}
\multirow{3}{*}{子词词表:} & `es' & `est' & `est$<$e$>$' & `lo' & `low' \\
& `ne' & `new'&`newest$<$e$>$' & `low$<$e$>$'& `wi'\\
& `wid' & `widest$<$e$>$' & `lowe' & `lower'& `lower$<$e$>$'
\end{tabular}};
\node[node,anchor=west] (line1) at ([xshift = 8em]node1.south east) {按字符拆分,并添加};
\node[node,anchor=north west] (line2) at ([yshift=0.3em]line1.south west) {终结符$<$e$>$,统计词频。};
\node[node,anchor=north west] (line3) at ([yshift=-4em]line2.south west) {统计每一个连续字节对};
\node[node,anchor=north west] (line4) at ([yshift=0.3em]line3.south west) {的出现频率,选择最高};
\node[node,anchor=north west] (line5) at ([yshift=0.3em]line4.south west) {频者合并成新的子词};
\begin{pgfonlayer}{background}
%\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=red!10,drop shadow,draw=red] [fit = (line1) (line2) (line3) (line4)] (box1) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,very thick,dotted,draw=purple] [fit = (node1) (node2)] (box1) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,very thick,dotted,draw=teal] [fit = (node3) (node4) (node5) (node6)] (box2) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=purple!5,drop shadow] [fit = (line1) (line2)] (box3) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=ugreen!5,drop shadow] [fit = (line3) (line4) (line5)] (box4) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=purple!5,drop shadow] [fit = (node7)] (box5) {};
\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=blue!5,drop shadow] [fit = (node8) (node9)] (box6) {};
\end{pgfonlayer}
\draw[->,line width=.03cm] ([yshift=0em]box2.south) -- ([yshift=0.2em]node7.north);
\draw[->,line width=.03cm] ([yshift=0em]box1.south) -- ([yshift=0em]box2.north);
\draw [->,dotted,very thick,purple] (box3.west) -- ([xshift=-1.5em]box3.west);
\draw [->,dotted,very thick,teal] (box4.west) -- ([xshift=-1.7em]box4.west);
\draw [->,dotted,very thick] ([xshift=6em]dict.north) .. controls +(north:1) and +(south:1) .. (box6.south);
\end{tikzpicture}
\ No newline at end of file
\begin{tikzpicture}
\node[rounded corners=3pt,minimum width=1.0em,minimum height=2.0em,font=\scriptsize,fill=green!5,drop shadow,thick,draw](top) at (0,0) {
\begin{tabular}{ll}
\multicolumn{2}{c}{BPE词表:} \\
errrr$<$e$>$ & tain$<$e$>$ \\
moun & est$<$e$>$ \\
high & the$<$e$>$ \\
a$<$e$>$ &
\end{tabular}
};
\node[font=\scriptsize,anchor=west] (node1) at ([xshift=0.5em,yshift=1em]top.east) {原始序列:};
\node[font=\scriptsize,anchor=west] (this) at (node1.east) {"this$<$e$>$" ,};
\node[font=\scriptsize,anchor=west] (highest) at (this.east) {"highest$<$e$>$",};
\node[font=\scriptsize,anchor=west] (mountain) at (highest.east) { "mountain$<$e$>$"};
\node[font=\scriptsize,anchor=west] (node2) at ([yshift=-1.5em]node1.south west) {BPE切分:};
\node[font=\scriptsize,anchor=west] (unk) at (node2.east) {"$<$unk$>$",};
\node[font=\scriptsize,anchor=west] (high) at (unk.east) {"high",};
\node[font=\scriptsize,anchor=west] (est) at (high.east) {"est$<$e$>$",};
\node[font=\scriptsize,anchor=west] (moun) at (est.east) {"moun",};
\node[font=\scriptsize,anchor=west] (tain) at (moun.east) {"tain$<$e$>$"};
%\draw[->,thick](node1.south) -- ([xshift=-1.0em]node2.north);
\draw[->,thick]([xshift=-0.2em]this.south) -- (unk);
\draw[->,thick](highest.south) -- (high);
\draw[->,thick](highest.south) -- (est);
\draw[->,thick](mountain.south) -- (moun);
\draw[->,thick](mountain.south) -- (tain);
\end{tikzpicture}
\ No newline at end of file
\begin{center}
\begin{tikzpicture}
\node[rounded corners=3pt,minimum width=10.0em,minimum height=2.0em,draw,thick,fill=green!5,font=\scriptsize,drop shadow,inner sep=0.5em] (left) at (0,0) {
\begin{tabular}{c}
名词\\
\rule{0pt}{12pt}cat,cats 、watch,watches\\
\rule{0pt}{12pt}baby,babies、wife,wives\\
\end{tabular}
};
\node[rounded corners=3pt,minimum width=10.0em,minimum height=2.0em,draw,thick,fill=green!5,font=\scriptsize,drop shadow,inner sep=0.5em] (right) at ([xshift=8em]left.east) {
\begin{tabular}{c}
动词\\
\rule{0pt}{12pt}do,did ,does,doing,done\\
\rule{0pt}{12pt}have,had,has,having\\
\end{tabular}
};
\end{tikzpicture}
\end{center}
\ No newline at end of file
\begin{tikzpicture}
\node[] (do) at (0,0) {{\red do}};
\node[anchor = west] (does) at ([xshift = 1em]do.east) {{\red do}es};
\node[anchor = west] (doing) at ([xshift = 0.7em]does.east) {{\red do}ing};
\node[anchor = north] (do_root) at ([yshift = -1.5em]does.south) {do};
\node[anchor = west] (new) at ([xshift = 2em]doing.east) {{\red new}};
\node[anchor = west] (newer) at ([xshift = 1em]new.east) {{\red new}er};
\node[anchor = west] (newest) at ([xshift = 0.7em]newer.east) {{\red new}est};
\node[anchor = north] (new_root) at ([yshift = -1.5em]newer.south) {new};
\draw [->] ([yshift=0.2em]do_root.north) .. controls +(north:0.4) and +(south:0.6) ..(do.south);
\draw [->] (do_root.north) -- (does.south);
\draw [->] ([yshift=0.2em]do_root.north) .. controls +(north:0.4) and +(south:0.6) ..(doing.south);
\draw [->] ([yshift=0.2em]new_root.north) .. controls +(north:0.4) and +(south:0.6) ..(new.south);
\draw [->] (new_root.north) -- (newer.south);
\draw [->] ([yshift=0.2em]new_root.north) .. controls +(north:0.4) and +(south:0.6) ..(newest.south);
\end{tikzpicture}
\ No newline at end of file
...@@ -5893,6 +5893,50 @@ author = {Yoshua Bengio and ...@@ -5893,6 +5893,50 @@ author = {Yoshua Bengio and
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 13------------------------------------------------------ %%%%% chapter 13------------------------------------------------------
@inproceedings{garcia-martinez2016factored,
title={Factored Neural Machine Translation Architectures},
author={Mercedes {Garcia-Martinez} and Loïc {Barrault} and Fethi {Bougares}},
booktitle={International Workshop on Spoken Language Translation (IWSLT'16)},
notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2949810612},
year={2016}
}
@inproceedings{DBLP:conf/acl/Kudo18,
author = {Taku Kudo},
title = {Subword Regularization: Improving Neural Network Translation Models
with Multiple Subword Candidates},
pages = {66--75},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@article{DBLP:journals/jmlr/RaffelSRLNMZLL20,
author = {Colin Raffel and
Noam Shazeer and
Adam Roberts and
Katherine Lee and
Sharan Narang and
Michael Matena and
Yanqi Zhou and
Wei Li and
Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text
Transformer},
journal = {Journal of Machine Learning Reseach},
volume = {21},
pages = {140:1--140:67},
year = {2020}
}
@inproceedings{DBLP:conf/icassp/SchusterN12,
author = {Mike Schuster and
Kaisuke Nakajima},
title = {Japanese and Korean voice search},
pages = {5149--5152},
publisher = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2012}
}
%%%%% chapter 13------------------------------------------------------ %%%%% chapter 13------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论