complete pages of modeling phrase-based derivations

Section04-Phrasal-and-Syntactic-Models/section04-test.tex

@@ -56,6 +56,13 @@
 
 \usefonttheme[onlylarge]{structurebold}
 
+\newlength{\mystep}
+\newlength{\base}
+\newlength{\wseg}
+\newlength{\hseg}
+\newlength{\wnode}
+\newlength{\hnode}
+
 \IfFileExists{C:/WINDOWS/win.ini}
 {\newcommand{\mycfont}{you}}
 {\newcommand{\mycfont}{gbsn}}
@@ -135,12 +142,85 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
     \item \textbf{翻译建模}：如何描述$\textrm{P}(d,\textbf{t}|\textbf{s})$
     \item \textbf{模型简化}：如何对所有$d$进行$\textrm{P}(d,\textbf{t}|\textbf{s})$的求和
     \end{itemize}
-    下面会分别展开讨论
-\item 回到一开始的问题: 给定$\textbf{s}$和$\textbf{t}$，如何获得双语短语
+    后面会分别展开讨论
+\vspace{0.3em}
+\item<2-> 回到一开始的问题: 给定$\textbf{s}$和$\textbf{t}$，\alert{如何获得双语短语}
     \begin{itemize}
     \item 如果没有限制，$\textbf{s}$和$\textbf{t}$之间任何子串映射都可以看做双语短语
     \end{itemize}
 \end{itemize}
+
+\vspace{-0.7em}
+
+\visible<2->{
+\begin{center}
+\begin{tikzpicture}
+
+\setlength{\wseg}{1.5cm}
+\setlength{\hseg}{1.0cm}
+\setlength{\wnode}{3.75cm}
+\setlength{\hnode}{1.0cm}
+
+\tikzstyle{elementnode} = [rectangle,text=white,anchor=center]
+\tikzstyle{srcnode} = [rotate=45,font=\small,anchor=south west]
+\tikzstyle{tgtnode} = [left,font=\small,anchor=north east]
+\tikzstyle{alignmentnode} = [rectangle,draw,minimum height=3.6\hnode,minimum width=0.36\hnode]
+\tikzstyle{probnode} = [fill=blue!30,minimum width=0.4\hnode]
+\tikzstyle{labelnode} = [above]
+
+% alignment matrix
+\begin{scope}[scale=0.85,yshift=0.12in]
+\foreach \i / \j / \c in
+    {0/7/0.15, 1/7/0.15, 2/7/0.15, 3/7/0.15, 4/7/0.15, 5/7/0.15,
+    0/6/0.15, 1/6/0.15, 2/6/0.15, 3/6/0.15, 4/6/0.15, 5/6/0.15,
+    0/5/0.15, 1/5/0.15, 2/5/0.15, 3/5/0.15, 4/5/0.15, 5/5/0.15,
+    0/4/0.15, 1/4/0.15, 2/4/0.15, 3/4/0.15, 4/4/0.15, 5/4/0.15,
+    0/3/0.15, 1/3/0.15, 2/3/0.15, 3/3/0.15, 4/3/0.15, 5/3/0.15,
+    0/2/0.15, 1/2/0.15, 2/2/0.15, 3/2/0.15, 4/2/0.15, 5/2/0.15,
+    0/1/0.15, 1/1/0.15, 2/1/0.15, 3/1/0.15, 4/1/0.15, 5/1/0.15,
+    0/0/0.15, 1/0/0.15, 2/0/0.15, 3/0/0.15, 4/0/0.15, 5/0/0.15}
+    \node[elementnode,minimum size=0.6*\hnode*\c,inner sep=0.1pt,fill=blue] (a\i\j) at (0.5*\hnode*\i-5.4*0.5*\hnode,0.5*\hnode*\j-1.05*\hnode) {};
+
+% source
+\node[srcnode] (src1) at (-5.4*0.5*\hnode,-1.05*\hnode+7.5*0.5*\hnode) {\scriptsize{Have}};
+\node[srcnode] (src2) at ([xshift=0.5\hnode]src1.south west) {\scriptsize{you}};
+\node[srcnode] (src3) at ([xshift=0.5\hnode]src2.south west) {\scriptsize{learned}};
+\node[srcnode] (src4) at ([xshift=0.5\hnode]src3.south west) {\scriptsize{nothing}};
+\node[srcnode] (src5) at ([xshift=0.5\hnode]src4.south west) {\scriptsize{?}};
+\node[srcnode] (src6) at ([xshift=0.5\hnode]src5.south west) {\scriptsize{EOS}};
+
+% target
+\node[tgtnode] (tgt1) at (-6.0*0.5*\hnode,-1.05*\hnode+7.5*0.5*\hnode) {\scriptsize{你}};
+\node[tgtnode] (tgt2) at ([yshift=-0.5\hnode]tgt1.north east) {\scriptsize{什么}};
+\node[tgtnode] (tgt3) at ([yshift=-0.5\hnode]tgt2.north east) {\scriptsize{都}};
+\node[tgtnode] (tgt4) at ([yshift=-0.5\hnode]tgt3.north east) {\scriptsize{没}};
+\node[tgtnode] (tgt5) at ([yshift=-0.5\hnode]tgt4.north east) {\scriptsize{学}};
+\node[tgtnode] (tgt6) at ([yshift=-0.5\hnode]tgt5.north east) {\scriptsize{到}};
+\node[tgtnode] (tgt7) at ([yshift=-0.5\hnode]tgt6.north east) {\scriptsize{?}};
+\node[tgtnode] (tgt8) at ([yshift=-0.5\hnode]tgt7.north east) {\scriptsize{EOS}};
+
+\node [anchor=west] (p1line1) at ([xshift=4em,yshift=1em]a57.east) {\footnotesize{$\tilde{s}_i$: 什么\ \ \ 都\ \ \ 没}};
+\node [anchor=north west] (p1line2) at ([xshift=0]p1line1.south west) {\footnotesize{$\tilde{t}_i$: learned\ \ \ nothing\ \ \ ? \ \ \ \ \ \ \ \ \ \ \ \ }};
+
+\node [anchor=west] (p2line1) at ([xshift=4em]a53.east) {\footnotesize{$\tilde{s}_j$: 到\ \ \ ?}};
+\node [anchor=north west] (p2line2) at ([xshift=0]p2line1.south west) {\footnotesize{$\tilde{t}_j$: Have\ \ \ you\ \ \ learned\ \ \ nothing}};
+
+\begin{pgfonlayer}{background}
+\node [rectangle,draw=red,thick,inner sep=0.2em,fill=white,drop shadow] [fit = (a26) (a44)] (phrase1) {};
+\node [rectangle,draw=ugreen,thick,inner sep=0.2em,fill=white,drop shadow] [fit = (a01) (a32)] (phrase2) {};
+\node [rectangle,inner sep=0.2em,fill=red!10] [fit = (p1line1) (p1line2)] (box1) {};
+\node [rectangle,inner sep=0.2em,fill=green!10] [fit = (p2line1) (p2line2)] (box2) {};
+\end{pgfonlayer}
+
+\draw [->,thick,dotted] ([yshift=-0.8em]phrase1.east) .. controls +(east:1.5) and +(west:1) ..  (box1.west);
+\draw [->,thick,dotted] ([yshift=-0.0em]phrase2.east) .. controls +(east:2.0) and +(west:1) ..  ([yshift=1em]box2.west);
+
+\end{scope}
+
+\end{tikzpicture}
+\end{center}
+}
+
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------

Section04-Phrasal-and-Syntactic-Models/section04.tex

@@ -51,15 +51,12 @@
 \setbeamercolor{uppercolblue}{fg=white,bg=ublue}
 \setbeamercolor{lowercolblue}{fg=black,bg=blue!10}
 
-
-%\usetheme{default}
-%\usetheme{Darmstadt}
-%\usetheme{Madrid}
-%\usetheme{Frankfurt}
-%\usetheme{Dresden}
-%\usetheme{Boadilla}
-%\usecolortheme{dolphin}
-
+\newlength{\mystep}
+\newlength{\base}
+\newlength{\wseg}
+\newlength{\hseg}
+\newlength{\wnode}
+\newlength{\hnode}
 
 \usefonttheme[onlylarge]{structurebold}
 
@@ -1035,6 +1032,127 @@
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
+%%% 数学模型
+\begin{frame}{数学模型}
+\begin{itemize}
+\item \textbf{机器翻译}：对于输入的源语言句子$\textbf{s}$，找到最佳译文$\hat{\textbf{t}}$
+
+\begin{displaymath}
+\hat{\textbf{t}} = \argmax_{\textbf{t}} \textrm{P}(\textbf{t}|\textbf{s})
+\end{displaymath}
+
+其中$\textrm{P}(\textbf{t}|\textbf{s})$表示$\textbf{s}$到$\textbf{t}$的翻译概率
+
+\item 三个基本问题(回忆一下第三章)
+    \begin{enumerate}
+    \item 如何定义$\textrm{P}(\textbf{t}|\textbf{s})$ - 建模问题
+    \item 如何学习$\textrm{P}(\textbf{t}|\textbf{s})$的统计模型 - 训练问题
+    \item 如何找到最优译文 - 解码问题
+    \end{enumerate}
+\vspace{0.3em}
+\item<2-> 先看建模问题。可以把$\textrm{P}(\textbf{t}|\textbf{s})$表示成所有翻译推导的概率
+
+\begin{displaymath}
+\textrm{P}(\textbf{t}|\textbf{s}) = \sum_{d} \textrm{P}(d,\textbf{t}|\textbf{s})
+\end{displaymath}
+
+$d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P}(d,\textbf{t}|\textbf{s})$表示翻译推导$d$的概率
+
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 翻译推导的建模
+\begin{frame}{对翻译推导进行建模}
+\begin{itemize}
+\item $\textrm{P}(\textbf{t}|\textbf{s}) = \sum_{d} \textrm{P}(d,\textbf{t}|\textbf{s})$带来新的问题：
+    \begin{itemize}
+    \item \textbf{短语获取}：如何获取双语短语，以构成$d$
+    \item \textbf{翻译建模}：如何描述$\textrm{P}(d,\textbf{t}|\textbf{s})$
+    \item \textbf{模型简化}：如何对所有$d$进行$\textrm{P}(d,\textbf{t}|\textbf{s})$的求和
+    \end{itemize}
+    后面会分别展开讨论
+\vspace{0.3em}
+\item<2-> 回到一开始的问题: 给定$\textbf{s}$和$\textbf{t}$，\alert{如何获得双语短语}
+    \begin{itemize}
+    \item 如果没有限制，$\textbf{s}$和$\textbf{t}$之间任何子串映射都可以看做双语短语
+    \end{itemize}
+\end{itemize}
+
+\vspace{-0.7em}
+
+\visible<2->{
+\begin{center}
+\begin{tikzpicture}
+
+\setlength{\wseg}{1.5cm}
+\setlength{\hseg}{1.0cm}
+\setlength{\wnode}{3.75cm}
+\setlength{\hnode}{1.0cm}
+
+\tikzstyle{elementnode} = [rectangle,text=white,anchor=center]
+\tikzstyle{srcnode} = [rotate=45,font=\small,anchor=south west]
+\tikzstyle{tgtnode} = [left,font=\small,anchor=north east]
+\tikzstyle{alignmentnode} = [rectangle,draw,minimum height=3.6\hnode,minimum width=0.36\hnode]
+\tikzstyle{probnode} = [fill=blue!30,minimum width=0.4\hnode]
+\tikzstyle{labelnode} = [above]
+
+% alignment matrix
+\begin{scope}[scale=0.85,yshift=0.12in]
+\foreach \i / \j / \c in
+    {0/7/0.15, 1/7/0.15, 2/7/0.15, 3/7/0.15, 4/7/0.15, 5/7/0.15,
+    0/6/0.15, 1/6/0.15, 2/6/0.15, 3/6/0.15, 4/6/0.15, 5/6/0.15,
+    0/5/0.15, 1/5/0.15, 2/5/0.15, 3/5/0.15, 4/5/0.15, 5/5/0.15,
+    0/4/0.15, 1/4/0.15, 2/4/0.15, 3/4/0.15, 4/4/0.15, 5/4/0.15,
+    0/3/0.15, 1/3/0.15, 2/3/0.15, 3/3/0.15, 4/3/0.15, 5/3/0.15,
+    0/2/0.15, 1/2/0.15, 2/2/0.15, 3/2/0.15, 4/2/0.15, 5/2/0.15,
+    0/1/0.15, 1/1/0.15, 2/1/0.15, 3/1/0.15, 4/1/0.15, 5/1/0.15,
+    0/0/0.15, 1/0/0.15, 2/0/0.15, 3/0/0.15, 4/0/0.15, 5/0/0.15}
+    \node[elementnode,minimum size=0.6*\hnode*\c,inner sep=0.1pt,fill=blue] (a\i\j) at (0.5*\hnode*\i-5.4*0.5*\hnode,0.5*\hnode*\j-1.05*\hnode) {};
+
+% source
+\node[srcnode] (src1) at (-5.4*0.5*\hnode,-1.05*\hnode+7.5*0.5*\hnode) {\scriptsize{Have}};
+\node[srcnode] (src2) at ([xshift=0.5\hnode]src1.south west) {\scriptsize{you}};
+\node[srcnode] (src3) at ([xshift=0.5\hnode]src2.south west) {\scriptsize{learned}};
+\node[srcnode] (src4) at ([xshift=0.5\hnode]src3.south west) {\scriptsize{nothing}};
+\node[srcnode] (src5) at ([xshift=0.5\hnode]src4.south west) {\scriptsize{?}};
+\node[srcnode] (src6) at ([xshift=0.5\hnode]src5.south west) {\scriptsize{EOS}};
+
+% target
+\node[tgtnode] (tgt1) at (-6.0*0.5*\hnode,-1.05*\hnode+7.5*0.5*\hnode) {\scriptsize{你}};
+\node[tgtnode] (tgt2) at ([yshift=-0.5\hnode]tgt1.north east) {\scriptsize{什么}};
+\node[tgtnode] (tgt3) at ([yshift=-0.5\hnode]tgt2.north east) {\scriptsize{都}};
+\node[tgtnode] (tgt4) at ([yshift=-0.5\hnode]tgt3.north east) {\scriptsize{没}};
+\node[tgtnode] (tgt5) at ([yshift=-0.5\hnode]tgt4.north east) {\scriptsize{学}};
+\node[tgtnode] (tgt6) at ([yshift=-0.5\hnode]tgt5.north east) {\scriptsize{到}};
+\node[tgtnode] (tgt7) at ([yshift=-0.5\hnode]tgt6.north east) {\scriptsize{?}};
+\node[tgtnode] (tgt8) at ([yshift=-0.5\hnode]tgt7.north east) {\scriptsize{EOS}};
+
+\node [anchor=west] (p1line1) at ([xshift=4em,yshift=1em]a57.east) {\footnotesize{$\tilde{s}_i$: 什么\ \ \ 都\ \ \ 没}};
+\node [anchor=north west] (p1line2) at ([xshift=0]p1line1.south west) {\footnotesize{$\tilde{t}_i$: learned\ \ \ nothing\ \ \ ? \ \ \ \ \ \ \ \ \ \ \ \ }};
+
+\node [anchor=west] (p2line1) at ([xshift=4em]a53.east) {\footnotesize{$\tilde{s}_j$: 到\ \ \ ?}};
+\node [anchor=north west] (p2line2) at ([xshift=0]p2line1.south west) {\footnotesize{$\tilde{t}_j$: Have\ \ \ you\ \ \ learned\ \ \ nothing}};
+
+\begin{pgfonlayer}{background}
+\node [rectangle,draw=red,thick,inner sep=0.2em,fill=white,drop shadow] [fit = (a26) (a44)] (phrase1) {};
+\node [rectangle,draw=ugreen,thick,inner sep=0.2em,fill=white,drop shadow] [fit = (a01) (a32)] (phrase2) {};
+\node [rectangle,inner sep=0.2em,fill=red!10] [fit = (p1line1) (p1line2)] (box1) {};
+\node [rectangle,inner sep=0.2em,fill=green!10] [fit = (p2line1) (p2line2)] (box2) {};
+\end{pgfonlayer}
+
+\draw [->,thick,dotted] ([yshift=-0.8em]phrase1.east) .. controls +(east:1.5) and +(west:1) ..  (box1.west);
+\draw [->,thick,dotted] ([yshift=-0.0em]phrase2.east) .. controls +(east:2.0) and +(west:1) ..  ([yshift=1em]box2.west);
+
+\end{scope}
+
+\end{tikzpicture}
+\end{center}
+}
+
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
 \subsection{短语抽取}
 
 %%%------------------------------------------------------------------------------------------------------------