Skip to content

T
Toy-MT-Introduction
Commit 05e8631a by 曹润柘
Options

更新 section06.tex

parent eb1ece19
正在显示 包含 43 行增加 和 33 行删除
Section06-Neural-Machine-Translation/section06.tex
...@@ -210,23 +210,33 @@ ...@@ -210,23 +210,33 @@
\begin{scope}[local bounding box=WMT] \begin{scope}[local bounding box=WMT]
\draw[->,thick] (0.5,0) to (10,0); \draw[->,thick] (0.5,0) to (10,0);
\draw[->,thick] (0.5,-0) to (0.5,3.5); \draw[->,thick] (0.5,-0) to (0.5,3.5);
\draw[thick] (0.4,1.6) to (0.6,1.6);
\draw[thick] (0.4,3.2) to (0.6,3.2);
\node[font=\scriptsize] at (0,2) {10};
\node[font=\scriptsize] at (0,3.2) {20};
%\normalsize
% 2015 % 2015
\node[minimum width=0.5cm,thick,minimum height=7*0.2cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2015) at (1.5,0.5pt) {}; \node[minimum width=0.5cm,thick,minimum height=7*0.16cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2015) at (1.5*0.7,0.5pt) {};
\node[minimum width=0.5cm,thick,minimum height=2*0.2cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2015) at (smt2015.south east) {}; \node[minimum width=0.5cm,thick,minimum height=2*0.16cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2015) at (smt2015.south east) {};
\node[font=\normalsize,anchor=north] () at (smt2015.south east) {2015}; \node[font=\normalsize,anchor=north] () at ([yshift=-0.2em]smt2015.south east) {2015};
% 2016 % 2016
\node[minimum width=0.5cm,thick,minimum height=3*0.2cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2016) at ($(nmt2015.south east)+(1,0)$) {}; \node[minimum width=0.5cm,thick,minimum height=3*0.16cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2016) at ($(nmt2015.south east)+(0.7,0)$) {};
\node[minimum width=0.5cm,thick,minimum height=8*0.2cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2016) at (smt2016.south east) {}; \node[minimum width=0.5cm,thick,minimum height=8*0.16cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2016) at (smt2016.south east) {};
\node[font=\normalsize,anchor=north] () at (smt2016.south east) {2016}; \node[font=\normalsize,anchor=north] () at ([yshift=-0.2em]smt2016.south east) {2016};
% 2017 % 2017
\node[minimum width=0.5cm,thick,minimum height=3*0.2cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2017) at ($(nmt2016.south east)+(1,0)$) {}; \node[minimum width=0.5cm,thick,minimum height=3*0.16cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2017) at ($(nmt2016.south east)+(0.7,0)$) {};
\node[minimum width=0.5cm,thick,minimum height=13*0.2cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2017) at (smt2017.south east) {}; \node[minimum width=0.5cm,thick,minimum height=13*0.16cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2017) at (smt2017.south east) {};
\node[font=\normalsize,anchor=north] () at (smt2017.south east) {2017}; \node[font=\normalsize,anchor=north] () at ([yshift=-0.2em]smt2017.south east) {2017};
% 2018 % 2018
\node[minimum width=0.5cm,thick,minimum height=0cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2018) at ($(nmt2017.south east)+(1,0)$) {}; \node[minimum width=0.5cm,thick,minimum height=0cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2018) at ($(nmt2017.south east)+(0.7,0)$) {};
\node[minimum width=0.5cm,thick,minimum height=14*0.2cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2018) at (smt2018.south east) {}; \node[minimum width=0.5cm,thick,minimum height=14*0.16cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2018) at (smt2018.south east) {};
\node[font=\normalsize,anchor=north] () at (smt2018.south east) {2018}; \node[font=\normalsize,anchor=north] () at ([yshift=-0.2em]smt2018.south east) {2018};
% 2019
\node[minimum width=0.5cm,thick,minimum height=0cm,draw,fill=blue!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (smt2019) at ($(nmt2018.south east)+(0.7,0)$) {};
\node[minimum width=0.5cm,thick,minimum height=21*0.16cm,draw,fill=red!30!white,inner sep=0pt,outer sep=0pt,anchor=south west] (nmt2019) at (smt2019.south east) {};
\node[font=\normalsize,anchor=north] () at ([yshift=-0.2em]smt2019.south east) {2019};
\end{scope} \end{scope}
% legend % legend
...@@ -1565,15 +1575,15 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\ ...@@ -1565,15 +1575,15 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
\end{scope} \end{scope}
\begin{scope} \begin{scope}
\node[wordnode,anchor=south] () at ([xshift=0.5\base]aux21) {$h_{t-1}$}; \node[wordnode,anchor=south] () at ([xshift=0.5\base]aux21) {$\mathbf{h}_{t-1}$};
\node[wordnode,anchor=west] () at (aux12) {$x_t$}; \node[wordnode,anchor=west] () at (aux12) {$\mathbf{x}_t$};
\node[wordnode,anchor=south] () at ([xshift=0.5\base]aux51) {$c_{t-1}$}; \node[wordnode,anchor=south] () at ([xshift=0.5\base]aux51) {$\mathbf{c}_{t-1}$};
\visible<3->{ \visible<3->{
\node[wordnode,anchor=south] () at ([xshift=-0.5\base]aux59) {$c_{t}$}; \node[wordnode,anchor=south] () at ([xshift=-0.5\base]aux59) {$\mathbf{c}_{t}$};
} }
\visible<4->{ \visible<4->{
\node[wordnode,anchor=east] () at (aux68) {$h_{t}$}; \node[wordnode,anchor=east] () at (aux68) {$\mathbf{h}_{t}$};
\node[wordnode,anchor=south] () at ([xshift=-0.5\base]aux29) {$h_{t}$}; \node[wordnode,anchor=south] () at ([xshift=-0.5\base]aux29) {$\mathbf{h}_{t}$};
} }
\end{scope} \end{scope}
...@@ -1584,27 +1594,27 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\ ...@@ -1584,27 +1594,27 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
\begin{scope} \begin{scope}
\visible<1->{ \visible<1->{
% forget gate formula % forget gate formula
\node[formulanode,anchor=south east,text width=3.4cm] () at ([shift={(4\base,1.5\base)}]aux51) {遗忘门\\$f_t=\sigma(W_f[h_{t-1},x_t]+b_f)$}; \node[formulanode,anchor=south east,text width=3.4cm] () at ([shift={(4\base,1.5\base)}]aux51) {遗忘门\\$\mathbf{f}_t=\sigma(\mathbf{W}_f[\mathbf{h}_{t-1},\mathbf{x}_t]+\mathbf{b}_f)$};
} }
\visible<2->{ \visible<2->{
% input gate formula % input gate formula
\node[formulanode,anchor=north east] () at ([shift={(4\base,-1.5\base)}]aux21) {输入门\\$i_t=\sigma(W_i[h_{t-1},x_t]+b_i)$\\$\hat{c}_t=\mathrm{tanh}(W_c[h_{t-1},x_t]+b_c)$}; \node[formulanode,anchor=north east] () at ([shift={(4\base,-1.5\base)}]aux21) {输入门\\$\mathbf{i}_t=\sigma(\mathbf{W}_i[\mathbf{h}_{t-1},\mathbf{x}_t]+\mathbf{b}_i)$\\$\hat{\mathbf{c}}_t=\mathrm{tanh}(\mathbf{W}_c[\mathbf{h}_{t-1},\mathbf{x}_t]+\mathbf{b}_c)$};
} }
\visible<3->{ \visible<3->{
% cell update formula % cell update formula
\node[formulanode,anchor=south west,text width=3.02cm] () at ([shift={(-4\base,1.5\base)}]aux59) {记忆更新\\$c_{t}=f_t\cdot c_{t-1}+i_t\cdot \hat{c}_t$}; \node[formulanode,anchor=south west,text width=3.02cm] () at ([shift={(-4\base,1.5\base)}]aux59) {记忆更新\\$\mathbf{c}_{t}=\mathbf{f}_t\cdot \mathbf{c}_{t-1}+\mathbf{i}_t\cdot \hat{\mathbf{c}}_t$};
} }
\visible<4->{ \visible<4->{
% output gate formula % output gate formula
\node[formulanode,anchor=north west] () at ([shift={(-4\base,-1.5\base)}]aux29) {输出门\\$o_t=\sigma(W_o[h_{t-1},x_t]+b_o)$\\$h_{t}=o_t\cdot \mathrm{tanh}(c_{t})$}; \node[formulanode,anchor=north west] () at ([shift={(-4\base,-1.5\base)}]aux29) {输出门\\$\mathbf{o}_t=\sigma(\mathbf{W}_o[\mathbf{h}_{t-1},\mathbf{x}_t]+\mathbf{b}_o)$\\$\mathbf{h}_{t}=\mathbf{o}_t\cdot \mathrm{tanh}(\mathbf{c}_{t})$};
} }
\end{scope} \end{scope}
\end{tikzpicture} \end{tikzpicture}
\end{center} \end{center}
{\scriptsize\begin{tabular}{l} {\scriptsize\begin{tabular}{l}
*$x_t$: 上一层的输出，$h_{t-1}$: 同一层上一时刻的隐藏状态\\ *$\mathbf{x}_t$: 上一层的输出，$\mathbf{h}_{t-1}$: 同一层上一时刻的隐藏状态\\
*$c_{t-1}$: 同一层上一时刻的记忆 *$\mathbf{c}_{t-1}$: 同一层上一时刻的记忆
\end{tabular}} \end{tabular}}
\end{frame} \end{frame}
...@@ -1735,11 +1745,11 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\ ...@@ -1735,11 +1745,11 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
\end{scope} \end{scope}
\begin{scope} \begin{scope}
\node[wordnode,anchor=south] () at (aux71) {$h_{t-1}$}; \node[wordnode,anchor=south] () at (aux71) {$\mathbf{h}_{t-1}$};
\node[wordnode,anchor=west] () at (aux12) {$x_t$}; \node[wordnode,anchor=west] () at (aux12) {$\mathbf{x}_t$};
\visible<3->{ \visible<3->{
\node[wordnode,anchor=east] () at (aux87) {$h_{t}$}; \node[wordnode,anchor=east] () at (aux87) {$\mathbf{h}_{t}$};
\node[wordnode,anchor=south] () at (aux78) {$h_{t}$}; \node[wordnode,anchor=south] () at (aux78) {$\mathbf{h}_{t}$};
} }
\end{scope} \end{scope}
...@@ -1750,23 +1760,23 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\ ...@@ -1750,23 +1760,23 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
\begin{scope} \begin{scope}
\visible<1->{ \visible<1->{
% reset gate formula % reset gate formula
\node[formulanode,anchor=west,text width=4cm] (reset) at ([shift={(\base,0.7\base)}]aux78) {重置门\\$r_t=\sigma(W_r[h_{t-1},x_t])$}; \node[formulanode,anchor=west,text width=4cm] (reset) at ([shift={(\base,0.7\base)}]aux78) {重置门\\$\mathbf{r}_t=\sigma(\mathbf{W}_r[\mathbf{h}_{t-1},\mathbf{x}_t])$};
} }
\visible<2->{ \visible<2->{
% update gate formula % update gate formula
\node[formulanode,anchor=north west,text width=4cm] (update) at ([yshift=-0.5\base]reset.south west) {更新门\\$u_t=\sigma(W_u[h_{t-1},x_t])$}; \node[formulanode,anchor=north west,text width=4cm] (update) at ([yshift=-0.5\base]reset.south west) {更新门\\$\mathbf{u}_t=\sigma(\mathbf{W}_u[\mathbf{h}_{t-1},\mathbf{x}_t])$};
} }
\visible<3->{ \visible<3->{
% hidden update formula % hidden update formula
\node[formulanode,anchor=north west,text width=4cm] () at ([yshift=-0.5\base]update.south west) {隐藏状态更新\\$\hat{h}_t=\mathrm{tanh}(W[r_t\cdot h_{t-1},x_t])$\\$h_{t}=(1-u_t)\cdot h_{t-1}+u_t\cdot \hat{h}_t$}; \node[formulanode,anchor=north west,text width=4cm] () at ([yshift=-0.5\base]update.south west) {隐藏状态更新\\$\hat{\mathbf{h}}_t=\mathrm{tanh}(\mathbf{W}[\mathbf{r}_t\cdot \mathbf{h}_{t-1},\mathbf{x}_t])$\\$\mathbf{h}_{t}=(1-\mathbf{u}_t)\cdot \mathbf{h}_{t-1}+\mathbf{u}_t\cdot \hat{\mathbf{h}}_t$};
} }
\end{scope} \end{scope}
\end{tikzpicture} \end{tikzpicture}
\end{center} \end{center}
{\footnotesize\begin{tabular}{l} {\footnotesize\begin{tabular}{l}
*$x_t$: 上一层的输出\\ *$\mathbf{x}_t$: 上一层的输出\\
*$h_{t-1}$: 同一层上一时刻的隐藏状态 *$\mathbf{h}_{t-1}$: 同一层上一时刻的隐藏状态
\end{tabular}} \end{tabular}}
\end{frame} \end{frame}
......
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