new updates

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

@@ -182,14 +182,59 @@
 %%%------------------------------------------------------------------------------------------------------------
 %%% 融合用双语短语描述翻译
 \begin{frame}{基于短语的翻译推导}
-\begin{itemize}
-\item 可以利用双语短语描述翻译过程\\
-\vspace{0.3em}
 \begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{定义 - 基于短语的翻译推导}
+{\small
 对于源语和目标语句对($\textbf{s}, \textbf{t}$)，有$l$个短语对$\{(\tilde{s}_i,\tilde{t}_j)\}$，且所有源语言短语$\{\tilde{s}_i\}$和所有目标语短语$\{\tilde{t}_j\}$分别构成$\textbf{s}$和$\textbf{t}$ 的切分，则称这些短语对$\{(\tilde{s}_i,\tilde{t}_j)\}$构成了$\textbf{s}$到$\textbf{t}$的\alert{基于短语的翻译推导}(简称推导)，记为$d(\{(\tilde{s}_i,\tilde{t}_j)\},\textbf{s},\textbf{t})$(简记为$d(\{(\tilde{s}_i,\tilde{t}_j)\})$或$d$)。
+}
 \end{beamerboxesrounded}
 
+\vspace{-0.5em}
+\begin{center}
+\begin{tikzpicture}
+ 
+\begin{scope}[minimum height = 18pt]
+ 
+\node[anchor=east] (s0) at (-0.5em, 0) {$\textbf{s}$:};
+\node[anchor=west] (s1) at (0, 0) {进口};
+\node[anchor=west] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west] (s3) at (7.9em, 0) {下降 了};
+ 
+\node[anchor=west,fill=ugreen!50] (s1) at (0, 0) {进口};
+\node[anchor=west,fill=red!50] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west,fill=blue!50] (s3) at (7.9em, 0) {下降 了};
+ 
+\node[anchor=east] (t0) at (-0.5em, -1) {$\textbf{t}$:};
+\node[anchor=west] (t1) at (0, -1) {the imports have};
+\node[anchor=west] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west] (t3) at (14.0em, -1) {fallen};
+ 
+\node[anchor=west,fill=ugreen!50] (t1) at (0, -1) {the imports have};
+\node[anchor=west,fill=red!50] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west,fill=blue!50] (t3) at (14.0em, -1) {fallen};
+ 
+\path[<->, thick] (s1.south) edge (t1.north);
+\path[<->, thick] (s2.south) edge (t2.north);
+\path[<->, thick] (s3.south) edge (t3.north);
+
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp1) at (s1.north) {\scriptsize{$\tilde{s}_1$}};
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp2) at (s2.north) {\scriptsize{$\tilde{s}_2$}};
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp3) at (s3.north) {\scriptsize{$\tilde{s}_3$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp1) at (t1.south) {\scriptsize{$\tilde{t}_1$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp2) at (t2.south) {\scriptsize{$\tilde{t}_2$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp3) at (t3.south) {\scriptsize{$\tilde{t}_3$}};
+ 
+\end{scope}
+\end{tikzpicture}
+\end{center}
+
+\vspace{-1.5em}
+
+\begin{itemize}
+\item $\{\tilde{s}_1,\tilde{s}_2,\tilde{s}_3\}$是$\textbf{s}$的一个短语切分
+\item $\{\tilde{t}_1,\tilde{t}_2,\tilde{t}_3\}$是$\textbf{t}$的一个短语切分
+\item $\{(\tilde{s}_k,\tilde{t}_k)\}$构成了$(\textbf{s},\textbf{t})$的一个基于短语的翻译推导
 \end{itemize}
+
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------

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

@@ -890,10 +890,188 @@
 \section{基于短语的模型}
 
 %%%------------------------------------------------------------------------------------------------------------
+\subsection{建模}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 什么是短语
+\begin{frame}{何为短语？}
+
+\begin{itemize}
+\item 句对可以用短语对的组合进行表示，比如下图的例子包含三个短语翻译：
+	\begin{itemize}
+	\item 进口 $\leftrightarrow$ the imports have
+	\item 大幅度 $\leftrightarrow$ drastically
+	\item 下降 了 $\leftrightarrow$ fallen
+	\end{itemize}
+
+\begin{center}
+\begin{tikzpicture}
+
+\begin{scope}[minimum height = 18pt]
+
+\node[anchor=east] (s0) at (-0.5em, 0) {源语:};
+\node[anchor=west] (s1) at (0, 0) {进口};
+\node[anchor=west] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west] (s3) at (7.9em, 0) {下降 了};
+
+\node[anchor=west,fill=ugreen!50] (s1) at (0, 0) {进口};
+\node [anchor=west,fill=red!50] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west,fill=blue!50] (s3) at (7.9em, 0) {下降 了};
+
+\node[anchor=east] (t0) at (-0.5em, -1) {目标语:};
+\node[anchor=west] (t1) at (0, -1) {the imports have};
+\node[anchor=west] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west] (t3) at (14.0em, -1) {fallen};
+
+\node[anchor=west,fill=ugreen!50] (t1) at (0, -1) {the imports have};
+\node[anchor=west,fill=red!50] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west,fill=blue!50] (t3) at (14.0em, -1) {fallen};
+
+\path[<->, thick] (s1.south) edge (t1.north);
+\path[<->, thick] (s2.south) edge (t2.north);
+\path[<->, thick] (s3.south) edge (t3.north);
+
+\end{scope}
+
+\end{tikzpicture}
+\end{center}
+
+\item<2-> 显然上图中的短语并不是语言学上的短语。这里有：\\
+
+\vspace{0.3em}
+\begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{定义 - 短语}
+对于一个句子$\textbf{w} = w_1...w_n$，任意子串$w_i...w_j$($i \le j$, $0 \le i$, $j \le n$)都是句子$\textbf{w}$的一个\alert{短语}
+\end{beamerboxesrounded}
+
+	\begin{itemize}
+	\item $n$个词构成的句子可以有$\frac{n(n+1)}{2}$个短语
+	\end{itemize}
+
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 什么是短语翻译推导
+\begin{frame}{双语短语}
+\begin{itemize}
+\item 进一步，可以定义 \\
+\begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{定义 - 句子的短语切分}
+对于一个句子$\textbf{w} = w_1...w_n$，可以被切分为$m$个子串，则称$\textbf{w}$由$m$个短语组成，记为$\textbf{w} = p_1...p_m$，其中$p_i$是$\textbf{w}$的一个短语， $p_1...p_m$也被称作句子$\textbf{w}$的一个\alert{短语切分}
+\end{beamerboxesrounded}
+
+\vspace{0.5em}
+\item<2-> 对于双语的情况 \\
+\begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{定义 - 双语短语(或短语对)}
+对于源语和目标语句对($\textbf{s}, \textbf{t}$)，$\textbf{s}$中短语$\tilde{s}_i$和$\textbf{t}$中的短语$\tilde{t}_j$可以构成一个双语短语对$(\tilde{s}_i,\tilde{t}_j)$，简称\alert{短语对}$(\tilde{s}_i,\tilde{t}_j)$
+\end{beamerboxesrounded}
+
+	\begin{itemize}
+	\item 比如，句对``进口 大幅度 下降 了 $\leftrightarrow$ the imports have drastically fallen''，有很多短语对，比如
+		\begin{itemize}
+		\item 大幅度 $\leftrightarrow$ drastically
+		\item 大幅度 下降 $\leftrightarrow$ have drastically fallen
+		\end{itemize}
+	\end{itemize}
+
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 融合用双语短语描述翻译
+\begin{frame}{基于短语的翻译推导}
+\begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{定义 - 基于短语的翻译推导}
+{\small
+对于源语和目标语句对($\textbf{s}, \textbf{t}$)，有$l$个短语对$\{(\tilde{s}_i,\tilde{t}_j)\}$，且所有源语言短语$\{\tilde{s}_i\}$和所有目标语短语$\{\tilde{t}_j\}$分别构成$\textbf{s}$和$\textbf{t}$ 的切分，则称这些短语对$\{(\tilde{s}_i,\tilde{t}_j)\}$构成了$\textbf{s}$到$\textbf{t}$的\alert{基于短语的翻译推导}(简称推导)，记为$d(\{(\tilde{s}_i,\tilde{t}_j)\},\textbf{s},\textbf{t})$(简记为$d(\{(\tilde{s}_i,\tilde{t}_j)\})$或$d$)。
+}
+\end{beamerboxesrounded}
+
+\vspace{-0.5em}
+\begin{center}
+\begin{tikzpicture}
+ 
+\begin{scope}[minimum height = 18pt]
+ 
+\node[anchor=east] (s0) at (-0.5em, 0) {$\textbf{s}$:};
+\node[anchor=west] (s1) at (0, 0) {进口};
+\node[anchor=west] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west] (s3) at (7.9em, 0) {下降 了};
+ 
+\node[anchor=west,fill=ugreen!50] (s1) at (0, 0) {进口};
+\node[anchor=west,fill=red!50] (s2) at (3.5em, 0) {大幅度};
+\node[anchor=west,fill=blue!50] (s3) at (7.9em, 0) {下降 了};
+ 
+\node[anchor=east] (t0) at (-0.5em, -1) {$\textbf{t}$:};
+\node[anchor=west] (t1) at (0, -1) {the imports have};
+\node[anchor=west] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west] (t3) at (14.0em, -1) {fallen};
+ 
+\node[anchor=west,fill=ugreen!50] (t1) at (0, -1) {the imports have};
+\node[anchor=west,fill=red!50] (t2) at (8.4em, -1) {drastically};
+\node[anchor=west,fill=blue!50] (t3) at (14.0em, -1) {fallen};
+ 
+\path[<->, thick] (s1.south) edge (t1.north);
+\path[<->, thick] (s2.south) edge (t2.north);
+\path[<->, thick] (s3.south) edge (t3.north);
+
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp1) at (s1.north) {\scriptsize{$\tilde{s}_1$}};
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp2) at (s2.north) {\scriptsize{$\tilde{s}_2$}};
+\node[anchor=south,inner sep=0pt,yshift=-0.3em] (sp3) at (s3.north) {\scriptsize{$\tilde{s}_3$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp1) at (t1.south) {\scriptsize{$\tilde{t}_1$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp2) at (t2.south) {\scriptsize{$\tilde{t}_2$}};
+\node[anchor=north,inner sep=0pt,yshift=0.3em] (tp3) at (t3.south) {\scriptsize{$\tilde{t}_3$}};
+ 
+\end{scope}
+\end{tikzpicture}
+\end{center}
+
+\vspace{-1.5em}
+
+\begin{itemize}
+\item $\{\tilde{s}_1,\tilde{s}_2,\tilde{s}_3\}$是$\textbf{s}$的一个短语切分
+\item $\{\tilde{t}_1,\tilde{t}_2,\tilde{t}_3\}$是$\textbf{t}$的一个短语切分
+\item $\{(\tilde{s}_k,\tilde{t}_k)\}$构成了$(\textbf{s},\textbf{t})$的一个基于短语的翻译推导
+\end{itemize}
+
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{短语抽取}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{判别式模型及特征}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{最小错误率训练}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{栈解码}
+
+%%%------------------------------------------------------------------------------------------------------------
 \section{基于层次短语的模型}
 
 %%%------------------------------------------------------------------------------------------------------------
+\subsection{同步上下文无关文法}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{层次短语规则及翻译特征}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{基于chart的解码}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{剪枝}
+
+%%%------------------------------------------------------------------------------------------------------------
 \section{基于语言学句法的模型}
 
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{基于树结构的文法}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{翻译规则抽取}
+
+%%%------------------------------------------------------------------------------------------------------------
+\subsection{规则匹配}
+
 \end{CJK}
 \end{document}