Merge branch 'master' of http://47.105.50.196/NiuTrans/Toy-MT-Introduction

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

@@ -125,76 +125,195 @@
 \section{基于层次短语的模型}
 
 %%%------------------------------------------------------------------------------------------------------------
-%%%  基于短语的系统的架构
-\begin{frame}{基于短语的系统的架构}
+\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}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%%  句法树(层次短语)
+\begin{frame}{层次短语句法树}
 \begin{itemize}
-\item \textbf{训练阶段}，需要得到三个子模型
-	\begin{enumerate}
-	\item 短语表：短语翻译及每个短语对应的特征值
-	\item 调序模型：短语调序的模型
-	\item 语言模型：评价译文流畅度的$n$-gram语言模型
-	\end{enumerate}
-\item \textbf{解码阶段}利用以上模型对新的句子进行翻译
+\item 层次短语规则的使用本质上在对(源语)句子构建树结构，它反应了文法对于字符串分析得到的推导
 \end{itemize}
 
 \begin{center}
 \begin{tikzpicture}
-\begin{scope}
 
-\tikzstyle{datanode} = [minimum width=7em,minimum height=1.7em,fill=ublue,rounded corners=0.7em];
-\tikzstyle{modelnode} = [minimum width=7em,minimum height=1.7em,fill=darkred,rounded corners=0.2em];
-\tikzstyle{decodingnode} = [minimum width=7em,minimum height=1.7em,fill=ugreen,rounded corners=0.2em];
+\begin{scope}[xshift = -0.5in, yshift = -3.2in, sibling distance=2pt, level distance = 27pt]
+\Tree[.\node(n1){\textbf{S}};
+        [.\node(n2){\textbf{S}};
+	        [.\node(n3){\textbf{S}};
+		        [.\node(n4){\textbf{S}};
+		            [.\node(n5){\textbf{X}}; \node(cw1){但}; ]
+		        ]
+		        [.\node(n6){\textbf{X}}; \node(cw2){美国}; ]
+		    ]
+	        [.\node(n7){\textbf{X}};
+	            [. \node(cw3){并没有}; ]
+	            [. \node(cw4){执行}; ]
+	        ]
+        ]
+        [.\node(n8){\textbf{X}};
+            [. \node(cw5){世贸}; ]
+            [.\node(n9){\textbf{X}};
+                [. \node(cw6){组织}; ]
+                [. \node(cw7){的}; ]
+            ]
+            [. \node(cw8){裁决}; ]
+        ]
+     ]
+
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = west] (l1) at ([xshift=-0.3em]n1.north east) {{\color{white} \tiny{$r_2$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = east] (l2) at ([xshift=0.3em]n2.north west) {{\color{white} \tiny{$r_2$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = east] (l2) at ([xshift=0.3em]n3.north west) {{\color{white} \tiny{$r_2$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = east] (l2) at ([xshift=0.3em]n4.north west) {{\color{white} \tiny{$r_1$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = east] (l2) at ([xshift=0.3em]n5.north west) {{\color{white} \tiny{$r_3$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = west] (l1) at ([xshift=-0.3em]n6.south east) {{\color{white} \tiny{$r_4$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = west] (l1) at ([xshift=-0.3em]n7.north east) {{\color{white} \tiny{$r_5$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = west] (l1) at ([xshift=-0.3em]n8.north east) {{\color{white} \tiny{$r_6$}}};
+\node[circle, inner sep = 1pt, fill=blue!90!white, anchor = west] (l1) at ([xshift=-0.3em]n9.north east) {{\color{white} \tiny{$r_7$}}};
+
+\end{scope}
+
+\begin{scope}[xshift = 1.8in, yshift = -3.0in]
+\node (rules) {\textbf{Rules used:}};
+\draw[-] (rules.south west)--([xshift=2.7in]rules.south west);
+
+\node[anchor=north west] (r1) at ([yshift=-0.2em]rules.south west) {$r_1$};
+\node[anchor=west] (rc1) at ([xshift=1em]r1.east) {$S \; \to \; X, \; \; X$};
+
+\node[anchor=north west] (r2) at ([yshift=-0.2em]r1.south west) {$r_2$};
+\node[anchor=west] (rc2) at ([xshift=1em]r2.east) {$S \; \to \; S \; X, \; \; S \; X$};
+
+\node[anchor=north west] (r3) at ([yshift=-0.2em]r2.south west) {$r_3$};
+\node[anchor=west] (rc3) at ([xshift=1em]r3.east) {$X \; \to \; \text{但}, \; \; \text{but}$};
 
-\node [datanode,anchor=north west] (bitext) at (0,0) {{\color{white} \scriptsize{训练用双语数据}}};
-\node [modelnode,anchor=north] (phrase) at ([yshift=-1.5em]bitext.south) {{\color{white} \scriptsize{短语抽取及打分}}};
-\node [modelnode,anchor=west] (reorder) at ([xshift=1.5em]phrase.east) {{\color{white} \scriptsize{调序建模}}};
-\node [modelnode,anchor=west] (lm) at ([xshift=1.5em]reorder.east) {{\color{white} \scriptsize{语言建模}}};
-\node [datanode,anchor=south] (monotext) at ([yshift=1.5em]lm.north) {{\color{white} \scriptsize{目标语单语数据}}};
+\node[anchor=north west] (r4) at ([yshift=-0.2em]r3.south west) {$r_4$};
+\node[anchor=west] (rc4) at ([xshift=1em]r4.east) {$X \; \to \; \text{美国}, \; \; \text{the U.S.}$};
 
-\node [datanode,anchor=north] (phrasetable) at ([yshift=-1.5em]phrase.south) {{\color{white} \scriptsize{短语表}}};
-\node [datanode,anchor=north] (reordertable) at ([yshift=-1.5em]reorder.south) {{\color{white} \scriptsize{调序模型}}};
-\node [datanode,anchor=north] (lmtable) at ([yshift=-1.5em]lm.south) {{\color{white} \scriptsize{语言模型}}};
+\node[anchor=north west] (r5) at ([yshift=-0.2em]r4.south west) {$r_5$};
+\node[anchor=west] (rc5) at ([xshift=1em]r5.east) {$X \; \to \; \text{并没有} \; \text{执行}, \; \; \text{}$};
 
-\node [decodingnode,anchor=north] (decoding) at ([yshift=-2em]reordertable.south) {{\color{white} \scriptsize{解码器}}};
+\node[anchor=north west] (r52) at ([yshift=-0.2em]r5.south west) {{\color{white} $r_5$}};
+\node[anchor=west] (rc52) at ([xshift=3.9em]r52.east) {$\text{has not implemented}$};
 
-\draw [->,very thick] ([yshift=-0.1em]bitext.south) -- ([yshift=0.1em]phrase.north);
-\draw [->,very thick] (bitext.south east) -- ([yshift=0.1em]reorder.north west);
-\draw [->,very thick] ([yshift=-0.1em]monotext.south) -- ([yshift=0.1em]lm.north);
-\draw [->,very thick] ([yshift=-0.1em]phrase.south) -- ([yshift=0.1em]phrasetable.north);
-\draw [->,very thick] ([yshift=-0.1em]reorder.south) -- ([yshift=0.1em]reordertable.north);
-\draw [->,very thick] ([yshift=-0.1em]lm.south) -- ([yshift=0.1em]lmtable.north);
+\node[anchor=north west] (r6) at ([yshift=-0.2em]r52.south west) {$r_6$};
+\node[anchor=west] (rc6) at ([xshift=1em]r6.east) {$X \; \to \; \text{世贸} \; X \; \text{裁决}, $};
 
-\draw [->,very thick] ([yshift=-0.1em]phrasetable.south east) -- ([yshift=0.1em,xshift=-3em]decoding.north);
-\draw [->,very thick] ([yshift=-0.1em]reordertable.south) -- ([yshift=0.1em,xshift=0em]decoding.north);
-\draw [->,very thick] ([yshift=-0.1em]lmtable.south west) -- ([yshift=0.1em,xshift=3em]decoding.north);
+\node[anchor=north west] (r61) at ([yshift=-0.2em]r6.south west) {{\color{white} $r_6$}};
+\node[anchor=west] (rc61) at ([xshift=3.9em]r61.east) {$\text{the decision} \; X \; \text{the WTO}$};
+
+\node[anchor=north west] (r7) at ([yshift=-0.2em]r61.south west) {$r_7$};
+\node[anchor=west] (rc7) at ([xshift=1em]r7.east) {$X \; \to \; \text{组织 的}, \; \; \text{of}$};
+
+\node (labela) at (-1in,-2.4in) {(b) Source-language projection of the derivation and the rules used};
 
 \end{scope}
+
 \end{tikzpicture}
 \end{center}
 
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
-%%%  文法驱动的统计机器翻译流程
-\begin{frame}{文法驱动的机器翻译流程}
-% Manual第42页
-\end{frame}
+%%%  句法树(语言学)
+\begin{frame}{语言学句法树}
+\begin{itemize}
+\item x
+\end{itemize}
 
+\begin{center}
+\begin{tikzpicture}
 
-%%%------------------------------------------------------------------------------------------------------------
-\subsection{同步上下文无关文法}
+\begin{scope}[xshift = -0.3in, sibling distance=18pt, level distance = 27pt]
+\Tree[.IP
+        [.ADVP
+            [.AD \node(cw1){但}; ]
+        ]
+        [.NP
+            [.NR \node(cw2){美国}; ]
+        ]
+        [.VP
+            [.ADVP
+                [.AD \node(cw3){并没有}; ]
+            ]
+            [.VP
+                [.VP
+                    [.VV \node(cw4){执行}; ]
+                ]
+                [.NP
+                    [.NP
+                        [.NN \node(cw5){世贸}; ]
+                        [.NN \node(cw6){组织}; ]
+                    ]
+                    [.DEC \node(cw7){的}; ]
+                    [.NP
+                        [.NN \node(cw8){裁决}; ]
+                    ]
+                ]
+            ]
+        ]
+     ]
+\node (labela) at (1in,-2.5in) {(a) The CTB-style parse tree of the input sentence};
+\end{scope}
+
+\end{tikzpicture}
+\end{center}
+
+\end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
-\subsection{层次短语规则及翻译特征}
+%%% 使用句法信息的一些思考
+\begin{frame}{使用句法信息的一些思考}
+\begin{itemize}
+\item \textbf{句法树形式选择} - 句法的表示形式有很多，侧重点也不同，机器翻译需要何种句法信息？
+\item \textbf{如何获取句法知识} - 句法信息由谁提供？
+    \begin{itemize}
+    \item 自动句法分析器可以提供句法信息，分析器可以从树库中自动学习(回忆第二章)，因此得到的句法分析结果和树库标注是一致的
+    \item 不使用句法分析器，而是让机器翻译自动学习适合翻译任务的句法结构
+    \end{itemize}
+\end{itemize}
+\end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
-\subsection{基于chart的解码}
+%%% 在MT中使用句法带来的好处
+\begin{frame}{使用句法的好处}
+\begin{itemize}
+\item 这里我们假设：
+    \begin{itemize}
+    \item 使用短语结构树表示句法信息
+    \item 句法树由句法分析器自动生成
+    \end{itemize}
+\item 短语结构树可以仍容易进行远距离调序的建模，同时丰富的句法功能标记有助于翻译中的消歧和生成
+\end{itemize}
+\end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
-\subsection{剪枝}
+%%% 句法树中的一些基本概念
+\begin{frame}{基本概念}
+\begin{itemize}
+\item 基于句法系统的一些基本概念
+\end{itemize}
+\end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
-\section{基于语言学句法的模型}
+%%% 句法模型分类
+\begin{frame}{句法模型分类}
+\begin{itemize}
+\item 句法模型分类
+\item 各种变形
+\end{itemize}
+\end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
 \subsection{基于树结构的文法}

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

@@ -840,7 +840,9 @@
 
  \begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=blue!5!white,colframe=blue!75!black,drop fuzzy shadow]
 {\LARGE
-\textbf{如何使用短语、句法等}\\ \textbf{结构信息进行机器翻译建模？}
+\textbf{如何使用短语、句法等}\\
+\\
+\textbf{结构信息进行机器翻译建模？}
 }
 \end{tcolorbox}
 
@@ -1532,15 +1534,15 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
 \visible<3->{
 % rule 1 (source)
 \node [anchor=west] (rule1s1) at (0,0) {与};
-\node [anchor=west,inner sep=2pt,fill=black] (rule1s2) at ([xshift=0.5em]rule1s1.east) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule1s2) at ([xshift=0.5em]rule1s1.east) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 \node [anchor=west] (rule1s3) at ([xshift=0.5em]rule1s2.east) {有};
-\node [anchor=west,inner sep=2pt,fill=black] (rule1s4) at ([xshift=0.5em]rule1s3.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule1s4) at ([xshift=0.5em]rule1s3.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 
 % rule 1 (target)
 \node [anchor=west] (rule1t1) at ([xshift=0.8in]rule1s4.east) {have};
-\node [anchor=west,inner sep=2pt,fill=black] (rule1t2) at ([xshift=0.5em]rule1t1.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule1t2) at ([xshift=0.5em]rule1t1.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 \node [anchor=west] (rule1t3) at ([xshift=0.5em]rule1t2.east) {with};
-\node [anchor=west,inner sep=2pt,fill=black] (rule1t4) at ([xshift=0.5em]rule1t3.east) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule1t4) at ([xshift=0.5em]rule1t3.east) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 }
 
 \visible<1->{
@@ -1573,14 +1575,14 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
 
 \visible<4->{
 % rule 2 (source)
-\node [anchor=west,inner sep=2pt,fill=black] (rule2s1) at ([yshift=3.5em,xshift=-0.5em]rule1s1.north west) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule2s1) at ([yshift=3.5em,xshift=-0.5em]rule1s1.north west) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 \node [anchor=west] (rule2s2) at ([xshift=0.5em]rule2s1.east) {的};
-\node [anchor=west,inner sep=2pt,fill=black] (rule2s3) at ([xshift=0.5em]rule2s2.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule2s3) at ([xshift=0.5em]rule2s2.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 
 % rule 2 (target)
-\node [anchor=west,inner sep=2pt,fill=black] (rule2t1) at ([xshift=1.8in]rule2s3.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule2t1) at ([xshift=1.8in]rule2s3.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 \node [anchor=west] (rule2t2) at ([xshift=0.5em]rule2t1.east) {that};
-\node [anchor=west,inner sep=2pt,fill=black] (rule2t3) at ([xshift=0.5em]rule2t2.east) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule2t3) at ([xshift=0.5em]rule2t2.east) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 
 % phrase 3 (source and target)
 \node [anchor=north] (phrase3s1) at ([yshift=-0.8em]rule2s3.south) {\footnotesize{少数 国家}};
@@ -1603,12 +1605,12 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
 
 \visible<5->{
 % rule 3 (source)
-\node [anchor=west,inner sep=2pt,fill=black] (rule3s1) at ([yshift=2.5em,xshift=4em]rule2s1.north west) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule3s1) at ([yshift=2.5em,xshift=4em]rule2s1.north west) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 \node [anchor=west] (rule3s2) at ([xshift=0.5em]rule3s1.east) {之一};
 
 % rule 3 (target)
 \node [anchor=west] (rule3t1) at ([xshift=1.0in]rule3s2.east) {one of};
-\node [anchor=west,inner sep=2pt,fill=black] (rule3t2) at ([xshift=0.5em]rule3t1.east) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule3t2) at ([xshift=0.5em]rule3t1.east) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 
 % edges: rule 2 to rule 3
 \draw [->] ([xshift=-1em]rule2s.north) ..controls +(north:1.2em) and +(south:1.2em).. ([yshift=-0.1em]rule3s1.south);
@@ -1625,14 +1627,14 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
 
 \visible<6->{
 % rule 4 (source)
-\node [anchor=west,inner sep=2pt,fill=black] (rule4s1) at ([yshift=3.5em,xshift=-3.5em]rule3s1.north west) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule4s1) at ([yshift=3.5em,xshift=-3.5em]rule3s1.north west) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 \node [anchor=west] (rule4s2) at ([xshift=0.5em]rule4s1.east) {是};
-\node [anchor=west,inner sep=2pt,fill=black] (rule4s3) at ([xshift=0.5em]rule4s2.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule4s3) at ([xshift=0.5em]rule4s2.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 
 % rule 2 (target)
-\node [anchor=west,inner sep=2pt,fill=black] (rule4t1) at ([xshift=2.0in]rule4s2.east) {\scriptsize{{\color{white} $X_1$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule4t1) at ([xshift=2.0in]rule4s2.east) {\scriptsize{{\color{white} $\textrm{X}_1$}}};
 \node [anchor=west] (rule4t2) at ([xshift=0.5em]rule4t1.east) {is};
-\node [anchor=west,inner sep=2pt,fill=black] (rule4t3) at ([xshift=0.5em]rule4t2.east) {\scriptsize{{\color{white} $X_2$}}};
+\node [anchor=west,inner sep=2pt,fill=black] (rule4t3) at ([xshift=0.5em]rule4t2.east) {\scriptsize{{\color{white} $\textrm{X}_2$}}};
 
 % phrase 4 (source and target)
 \node [anchor=north] (phrase4s1) at ([yshift=-0.8em]rule4s1.south) {\footnotesize{澳洲}};
@@ -1818,7 +1820,7 @@ d = r_1 \circ r_2 \circ r_3 \circ r_4
 \draw [->,very thick] ([yshift=-0.1em]monotext.south) -- ([yshift=0.1em]lm.north);
 \draw [->,very thick] ([yshift=-0.1em]lm.south) -- ([yshift=0.1em]lmmodel.north);
 \draw [->,very thick] ([yshift=0.3em,xshift=-0.1em]lmmodel.west) -- ([yshift=-0.1em]tuning.south east);
-\draw [->,very thick] ([yshift=-0.3em,xshift=-0.1em]lmmodel.west) -- ([yshift=-0.1em]decoding.north east);
+\draw [->,very thick] ([yshift=-0.3em,xshift=-0.1em]lmmodel.west) -- ([yshift=0.1em]decoding.north east);
 \end{scope}
 \end{tikzpicture}
 \end{center}