update the outline

Section06-Neural-Machine-Translation/section06-test.tex

@@ -170,6 +170,8 @@
 \end{itemize}
 \end{frame}
 
+
+
 %%%------------------------------------------------------------------------------------------------------------
 \section{Transformer}
 

Section06-Neural-Machine-Translation/section06.tex

@@ -548,7 +548,7 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
                 \draw[-latex'] (emb6.north) to (rnn6.south);
                 \draw[-latex'] (rnn5.east) to (rnn6.west);
                 \draw[-latex'] (rnn6.north) to (softmax3.south);
-                
+
                 \node[rnnnode,fill=blue!30!white,right=\base of rnn6] (rnn7) {};
                 \node[rnnnode,fill=green!30!white,below=\base of rnn7] (emb7) {};
                 \node[rnnnode,fill=red!30!white,above=\base of rnn7] (softmax4) {};
@@ -639,22 +639,23 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
 \textbf{入门：循环网络翻译模型及注意力机制} \\
 \small{1. 起源} \\
 \small{2. 模型结构} \\
-\small{3. 注意力机制}
+\small{3. 注意力机制} \\
+\small{4. 训练和推断}
 }
 \end{tcolorbox}
 
-\vspace{0.5em}
+\vspace{0.2em}
 
  \begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=red!5!white,colframe=red!75!black,drop fuzzy shadow]
 {\large
 \textbf{热门：Transformer} \\
-\small{1. 多头自注意力模型} \\
-\small{2. 训练及推断} \\
-\small{3. 深层网络翻译模型}
+\small{1. 自注意力模型} \\
+\small{2. 多头注意力和层正则化} \\
+\small{3. 更深、更宽的模型}
 }
 \end{tcolorbox}
 
-\vspace{0.5em}
+\vspace{0.2em}
 
 \begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=red!5!white,colframe=red!75!black,drop fuzzy shadow]
 {\large
@@ -1820,7 +1821,7 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
 
 \visible<3->{
 % alignment bars 2
-\node[probnode,anchor=south west,minimum height=0.4\hnode,inner sep=0.1pt,fill=red!40,label=below:\scriptsize{$0.4$}] (attn21) at ([xshift=2.3\hnode,yshift=-0.0\hnode]alignment2.east) {};
+\node[probnode,anchor=south west,minimum height=0.4\hnode,inner sep=0.1pt,fill=red!40,label=below:\scriptsize{$0.4$}] (attn21) at ([xshift=2.3\hnode,yshift=0.5\hnode]alignment2.east) {};
 \node[probnode,anchor=south west,minimum height=0.4\hnode,inner sep=0.1pt,fill=red!40,label=below:\scriptsize{$0.4$}] (attn22) at ([xshift=1pt]attn21.south east) {};
 \node[probnode,anchor=south west,minimum height=0.05\hnode,inner sep=0.1pt,fill=red!40,label=below:\scriptsize{$0$}] (attn23) at ([xshift=1pt]attn22.south east) {};
 \node[probnode,anchor=south west,minimum height=0.1\hnode,inner sep=0.1pt,fill=red!40,label=below:\scriptsize{$0.1$}] (attn24) at ([xshift=1pt]attn23.south east) {};
@@ -1840,12 +1841,14 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
 
 \visible<3->{
 % coverage score formula node
-\node[anchor=north west] (formula) at ([xshift=-0.3\hnode,yshift=-2.5\hnode]attn11.south) {\small{不同$C_i$所对应的源语言词的权重是不同的}};
+\node [anchor=north west] (formula) at ([xshift=-0.3\hnode,yshift=-1.5\hnode]attn11.south) {\small{不同$C_i$所对应的源语言词的权重是不同的}};
+\node [anchor=north west] (example) at (formula.south west) {\footnotesize{$C_2=0.4 \times h(\textrm{``你''}) + 0.4 \times h(\textrm{``什么''}) +$}};
+\node [anchor=north west] (example2) at ([yshift=0.4em]example.south west) {\footnotesize{$\ \ \ \ \ \ \ \ 0 \times h(\textrm{``都''}) + 0.1 \times h(\textrm{``没''}) + ..$}};
 }
 
 \visible<3->{
 % matrix -> attn2
-\draw[->,red] ([xshift=0.1em,yshift=2.3em]alignment2.east).. controls +(east:1.9cm) and +(west:1.0cm) ..([xshift=-0.15\hnode,yshift=-0.0\hnode]attn21.north west);
+\draw[->,red] ([xshift=0.1em,yshift=2.3em]alignment2.east).. controls +(east:1.9cm) and +(west:1.0cm) ..([xshift=-0.15\hnode,yshift=-1em]attn21.north west);
 }
 
 \visible<2->{
@@ -1854,7 +1857,7 @@ NLP问题的隐含结构假设 & 无隐含结构假设，端到端学习 \\
 
 \visible<3->{
 % attn2 -> cov2
-\draw[->] ([xshift=0.2\hnode,yshift=0.0\hnode]attn26.east)--([xshift=0.7\hnode,yshift=0.0\hnode]attn26.east) node[pos=0.5,above] (sum2) {\small{$\sum$}}; % 0.3 - 0.5 height of the
+\draw[->] ([xshift=0.2\hnode,yshift=0.0\hnode]attn26.east)--([xshift=0.7\hnode,yshift=0]attn26.east) node[pos=0.5,above] (sum2) {\small{$\sum$}}; % 0.3 - 0.5 height of the
 }
 
 \visible<2->{
@@ -1922,6 +1925,37 @@ $\textrm{``you''} = \argmax_{y} \textrm{P}(y|s_1, \alert{C})$ & $\textrm{``you''
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
+%%% 注意力模型的效果 - 热图
+\begin{frame}{真实的实例}
+\begin{itemize}
+\item 注意力的权重符合双语对应的规律
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 实验结果
+\begin{frame}{效果}
+%% 实用注意力机制带来的提升
+%% 个大评测比赛没有不使用注意力机制的系统，已经成为标配
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 训练
+\begin{frame}{训练}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 解码
+\begin{frame}{推断}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% GNMT
+\begin{frame}{成功案例 - GNMT}
+%% GNMT的图和几句话说它多牛
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
 \section{Transformer}
 
 %%%------------------------------------------------------------------------------------------------------------