Update RNN input & output figures

1485b49e · Lee · cbd21156 · 1485b49e
Commit 1485b49e authored Jan 04, 2020 by Lee
--- a/Section06-Neural-Machine-Translation/section06.tex
+++ b/Section06-Neural-Machine-Translation/section06.tex
@@ -1134,17 +1134,17 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
 %%%------------------------------------------------------------------------------------------------------------
 %%% 词嵌入
 \begin{frame}{模块1：词嵌入层}
-\begin{itemize}
-\item 词嵌入的作用是把离散化的单词表示转换为连续空间上的分布式表示
    \begin{itemize}
-    \item 把输入的词转换成唯一对应的词表大小的0-1向量
+    \item 词嵌入的作用是把离散化的单词表示转换为连续空间上的分布式表示
-    \item 根据0-1向量，从词嵌入矩阵中取出对应的词嵌入$e()$
+        \begin{itemize}
-    \item 取出的词嵌入$e()$作为循环神经网络的输入
+        \item<2-> 把输入的词转换成唯一对应的词表大小的0-1向量
-\end{itemize}
+        \item<3-> 根据0-1向量，从词嵌入矩阵中取出对应的词嵌入$e()$
-\end{itemize}
+        \item<4-> 取出的词嵌入$e()$作为循环神经网络的输入
-\vspace{-1em}
+    \end{itemize}
-%%% 图
+    \end{itemize}
-\begin{center}
+    \vspace{-1em}
+    %%% 图
+    \begin{center}
        \hspace*{-0.6cm}
        \begin{tikzpicture}
            \setlength{\base}{0.9cm}
@@ -1220,7 +1220,12 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
            \begin{scope}
                \coordinate (start) at (5.8\base,0.3\base);
+                \visible<2->{
                    \node [anchor=south west] (one) at (start) {\scriptsize{$\begin{bmatrix} 0 \\ 0 \\ 0 \\ \vdots \\ 0 \\ {\color{ugreen} 1} \\ 0 \\ 0 \end{bmatrix}$}};
+                }
+                \visible<3->{
+                    \node [draw=ugreen,fill=green!20!white,rounded corners=0.3em,minimum width=3.8cm,minimum height=0.9em,anchor=south west] (emb) at ([shift={(1.25cm,0.8cm)}]start) {};
+                }
                \node [anchor=north] (w) at ([yshift=3pt]one.south) {\scriptsize{\color{ugreen} you}};
                \node [anchor=north west] (words) at ([xshift=10pt]one.north east) {\scriptsize{$\begin{matrix} \langle\textrm{eos}\rangle \\ \langle\textrm{sos}\rangle \\ \textrm{Do} \\ \vdots \\ \textrm{know} \\ \textrm{you} \\ \textrm{?} \\ \textrm{have} \end{matrix}$}};
                \node [anchor=north west] (mat) at ([xshift=-6pt]words.north east) {\scriptsize{$
@@ -1233,17 +1238,17 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
                        -1 & -2 & \cdots & -3 \\
                        .7 &  .5 & \cdots & 3 \\
                        -2 & .3 & \cdots & .1
-                \end{bmatrix}$
+                    \end{bmatrix}
-            }};
+                $}};
-            \begin{pgfonlayer}{background}
-                \node [draw=ugreen,fill=green!20!white,rounded corners=0.3em,minimum width=3.8cm,minimum height=0.9em,anchor=south west] (emb) at ([shift={(1.25cm,0.8cm)}]start) {};
-            \end{pgfonlayer}
                \draw [decorate,decoration={brace,mirror}] ([shift={(6pt,2pt)}]mat.south west) to node [auto,swap,font=\scriptsize] {词嵌入矩阵} ([shift={(-6pt,2pt)}]mat.south east);
+                \visible<3->{
                    \draw [-latex'] ([xshift=-2pt,yshift=-0.65cm]one.east) to ([yshift=-0.65cm]words.west);
+                }
+                \visible<4->{
                    \draw [-latex'] (emb.east) -| ([yshift=0.4cm]mat.north east) node [pos=1,above] {\scriptsize{RNN输入}};
+                }
                \draw [-latex'] ([yshift=-0.4cm]w.south) to ([yshift=2pt]w.south);
                \node [anchor=north] (wlabel) at ([yshift=-0.6em]w.south) {\scriptsize{输入的单词}};
@@ -1252,21 +1257,21 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
            \draw [->,thick,densely dashed,ugreen] ([yshift=-0.2em]demb3.east) to [out=0,in=180] ([yshift=-1cm]input.west);
        \end{tikzpicture}
-\end{center}
+    \end{center}
 \end{frame}
 %%%------------------------------------------------------------------------------------------------------------
 %%% 输出
 \begin{frame}{模块2：输出层}
-\begin{itemize}
-\item 输出层需要得到每个目标语单词的生成概率，进而选取概率最高的词作为输出。但RNN中的隐藏层并不会输出单词概率，而是输出$s$，其每一行对应一个单词表示
    \begin{itemize}
-    \item $s$经过权重矩阵$W$变成$\hat{s}$，其隐藏层维度变换成词表的大小
+    \item 输出层需要得到每个目标语单词的生成概率，进而选取概率最高的词作为输出。但RNN中的隐藏层并不会输出单词概率，而是输出$s$，其每一行对应一个单词表示
-    \item $\hat{s}$经过Softmax变换得到不同词作为输出的概率，即单词$i$的概率$p_i = \textrm{Softmax}(i) = \frac{e^{\hat{s}_i}}{\sum_{j} e^{\hat{s}_{j}}} $
+        \begin{itemize}
+        \item<2-> $s$经过权重矩阵$W$变成$\hat{s}$，其隐藏层维度变换成词表的大小
+        \item<3-> $\hat{s}$经过Softmax变换得到不同词作为输出的概率，即单词$i$的概率$p_i = \textrm{Softmax}(i) = \frac{e^{\hat{s}_i}}{\sum_{j} e^{\hat{s}_{j}}} $
        \end{itemize}
-\end{itemize}
+    \end{itemize}
-%%% 图
+    %%% 图
-\begin{center}
+    \begin{center}
        \hspace*{-0.6cm}
        \begin{tikzpicture}
            \setlength{\base}{0.9cm}
@@ -1349,16 +1354,19 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
                \node [anchor=west,minimum width=1em,minimum size=1em,fill=white] (cell03) at (cell02.east) {\scriptsize{$\cdots$}};
                \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!50] (cell04) at (cell03.east) {\scriptsize{5}};
+                \visible<2->{
                    \node [anchor=south,minimum width=10.9em,minimum height=1.3em,draw,rounded corners=0.3em] (target) at ([yshift=1.5em]hidden.north) {};
                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!10] (cell11) at ([xshift=0.2em]target.west) {\scriptsize{-2}};
                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!10] (cell12) at (cell11.east) {\scriptsize{-1}};
-            \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!10] (cell13) at (cell12.east) {\scriptsize{.7}};
+                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!30] (cell13) at (cell12.east) {\scriptsize{.7}};
                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=white] (cell14) at (cell13.east) {\scriptsize{$\cdots$}};
-            \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!30] (cell15) at (cell14.east) {\scriptsize{6}};
+                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!70] (cell15) at (cell14.east) {\scriptsize{6}};
-            \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!70] (cell16) at (cell15.east) {\scriptsize{-3}};
+                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!10] (cell16) at (cell15.east) {\scriptsize{-3}};
                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!10] (cell17) at (cell16.east) {\scriptsize{-1}};
                    \node [anchor=west,minimum width=1em,minimum size=1em,fill=ugreen!20] (cell18) at (cell17.east) {\scriptsize{.2}};
+                }
+                \visible<3->{
                    \node [anchor=south,minimum width=1em,minimum height=0.2em,fill=ublue!80,inner sep=0pt] (label1) at ([yshift=2.5em]cell11.north) {};
                    \node [anchor=west,rotate=90,font=\tiny] (w1) at (label1.north) {$\langle$eos$\rangle$};
                    \node [anchor=south,minimum width=1em,minimum height=0.3em,fill=ublue!80,inner sep=0pt] (label2) at ([yshift=2.5em]cell12.north) {};
@@ -1367,26 +1375,38 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
                    \node [anchor=west,rotate=90,font=\tiny] (w3) at (label3.north) {Do};
                    \node [anchor=south,font=\scriptsize] (w4) at ([yshift=2.5em]cell14.north) {$\cdots$};
                    \node [anchor=south,minimum width=1em,minimum height=1em,fill=ublue!80,inner sep=0pt] (label5) at ([yshift=2.5em]cell15.north) {};
+                    \alt<4->
+                    {
                        \node [anchor=west,rotate=90,font=\tiny] (w5) at (label5.north) {{\color{red} know}};
+                    }
+                    {
+                        \node [anchor=west,rotate=90,font=\tiny] (w5) at (label5.north) {know};
+                    }
                    \node [anchor=south,minimum width=1em,minimum height=0.1em,fill=ublue!80,inner sep=0pt] (label6) at ([yshift=2.5em]cell16.north) {};
                    \node [anchor=west,rotate=90,font=\tiny] (w6) at (label6.north) {you};
                    \node [anchor=south,minimum width=1em,minimum height=0.3em,fill=ublue!80,inner sep=0pt] (label7) at ([yshift=2.5em]cell17.north) {};
                    \node [anchor=west,rotate=90,font=\tiny] (w7) at (label7.north) {?};
                    \node [anchor=south,minimum width=1em,minimum height=0.4em,fill=ublue!80,inner sep=0pt] (label8) at ([yshift=2.5em]cell18.north) {};
                    \node [anchor=west,rotate=90,font=\tiny] (w8) at (label8.north) {have};
+                }
+                \visible<2->{
                    \filldraw [fill=red!20,draw=white] (target.south west) -- (target.south east) -- ([xshift=-0.2em,yshift=0.1em]hidden.north east) -- ([xshift=0.2em,yshift=0.1em]hidden.north west);
                    \draw [->,thick] ([xshift=0.2em,yshift=0.1em]hidden.north west) -- (target.south west);
                    \draw [->,thick] ([xshift=-0.2em,yshift=0.1em]hidden.north east) -- (target.south east);
+                    \node [anchor=south] () at ([yshift=0.3em]hidden.north) {\scriptsize{$\hat{s}=Ws$}};
+                }
+                \visible<3->{
                    \node [rounded corners=0.3em] (softmax) at ([yshift=1.25em]target.north) {\scriptsize{$p(\hat{s}_i)=\frac{e^{\hat{s}_i}}{\sum_j e^{\hat{s}_j}}$}};
-            \begin{pgfonlayer}{background}
                    \filldraw [fill=blue!20,draw=white] ([yshift=0.1em]cell11.north west) {[rounded corners=0.3em] -- (softmax.west)} -- (label1.south west) -- (label8.south east) {[rounded corners=0.3em] -- (softmax.east)} -- ([yshift=0.1em]cell18.north east) -- ([yshift=0.1em]cell11.north west);
-            \end{pgfonlayer}
+                    \node [rounded corners=0.3em] (softmax) at ([yshift=1.25em]target.north) {\scriptsize{$p(\hat{s}_i)=\frac{e^{\hat{s}_i}}{\sum_j e^{\hat{s}_j}}$}};
+                }
-            \node [anchor=south] () at ([yshift=0.3em]hidden.north) {\scriptsize{$\hat{s}=Ws$}};
                \draw [-latex'] ([yshift=-0.3cm]hidden.south) to (hidden.south);
+                \visible<4->{
                    \draw [-latex'] (w5.east) to ([yshift=0.3cm]w5.east);
+                }
                \coordinate (tmp) at ([yshift=-3pt]w5.east);
                \node [draw=red,thick,densely dashed,rounded corners=3pt,inner sep=5pt,fit=(cell01) (cell11) (label1) (label8) (target) (hidden) (tmp)] (output) {};
@@ -1394,7 +1414,7 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
            \draw [->,thick,densely dashed,red] ([yshift=-0.2em]softmax3.east) .. controls +(east:2\base) and +(west:\base) .. (output.west);
        \end{tikzpicture}
-\end{center}
+    \end{center}
 \end{frame}
 %%%------------------------------------------------------------------------------------------------------------