spmt rules

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

@@ -146,30 +146,37 @@
 \subsection{翻译规则抽取}
 
 %%%------------------------------------------------------------------------------------------------------------
-%%%  组合规则
-\begin{frame}{更多的规则 - 组合规则}
+%%%  SPMT规则
+\begin{frame}{更多的规则 - SPMT规则}
 \begin{itemize}
-\item 最小规则之间可以进行组合，得到更大粒度的组合规则，可以使用更多上下文信息，并进行更复杂的调序。比如，三条最小规则组合成一条composed-3规则
+\item 任意大小的规则都可以通过组合的方式获取，但是组合过多数量的规则会大大增加规则集大小。SPMT一种高效地获得大颗粒度规则的方法 (Marcu et al., 2006)
+	\begin{itemize}
+	\item 先抽取短语，之后找到覆盖这个短语的可信节点
+	\item 以这个可信节点做根，生成包含该短语的规则
+	\end{itemize}
 \end{itemize}
 
+\vspace{-0.3em}
 \begin{minipage}[b]{0.47\textwidth}
 {\footnotesize
-\renewcommand*{\arraystretch}{1.3}
-\begin{tabular}{l l}
-\visible<2->{$r_1$} & \visible<2->{NP(PN(他)) $\to$  he} \\
-\visible<2->{$r_5$} & \visible<2->{PP(P$_1$ NP$_2$) $\to$ P$_1$ NP$_2$} \\
-\visible<2->{$r_6$} & \visible<2->{VP(PP$_1$ VP$_2$) $\to$ VP$_2$ PP$_1$} \\
-\visible<2->{$r_7$} & \visible<2->{IP(NP$_1$ VP$_2$) $\to$ NP$_1$ VP$_2$} \\
-\visible<3->{\alert{$r_{1,7}$}} & \visible<3->{IP(NP(PN(他)) VP$_1$) $\to$} \\
-                          & \visible<3->{he VP$_1$}\\
-\visible<4->{\alert{$r_{1,6}$}} & \visible<4->{IP(NP(PN(他)) VP(PP$_1$ VP$_2$))} \\
-\visible<4->{\alert{\ $^{,7}$}}  & \visible<4->{$\to$ he VP$_2$ PP$_1$}\\
-\visible<5->{\alert{$r_{1,5}$}} & \visible<5->{IP(NP(PN(他)) } \\
-\visible<5->{\alert{\ $^{,6,7}$}}  & \visible<5->{VP(P$_1$ NP$_2$ VP$_3$))}\\
-                           & \visible<5->{$\to$ he VP$_3$ P$_1$ NP$_2$}\\
-                           & \\
-\end{tabular}
-\renewcommand*{\arraystretch}{1.0}
+\visible<3->{
+对于任意一个与词对齐兼容的短语，可以找到包含它的``最小''翻译规则，即SPMT规则，比如\\
+
+\vspace{-0.4em}
+对 形式 $\to$ about the situation \\
+
+\vspace{-0.4em}
+可以很容易得到它的SPMT规则 \\
+
+\vspace{-0.4em}
+VP(P(对) NP(NN(局势)) VP$_1$) $\to$ VP$_1$ about the situation \\
+}
+
+\visible<4->{
+\vspace{-0.4em}
+但是，如果用组合的方式，需要三条最小规则才能得到这条规则\\
+}
+\vfill
 }
 \end{minipage}
 \hfill
@@ -192,35 +199,30 @@
 
 \begin{scope}[level distance=20pt]
 \node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag3) at
-   ([xshift=1.2em]cfrag2.south east) {\Tree[.\node(sn4){NP}; [.NN 回答 ]]};
+   ([xshift=1.2em]cfrag2.south east) {\Tree[.\node(sn4){NP}; [.NN 形式 ]]};
    \end{scope}
 
 \begin{scope}[sibling distance=15pt,level distance=20pt]
 \node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag4) at
-   ([xshift=1.4em]cfrag3.south east) {\Tree[.\node(sn5){VP}; [.\node(sn6){VV}; 表示 ] [.\node(sn7){NN}; 满意 ]]};
-\end{scope}
-
-\begin{scope}[sibling distance=20pt,,level distance=25pt]
-\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag5) at
-   ([xshift=0.3em,yshift=2.2em]cfrag2.north west) {\Tree[.\node(sn8){PP}; [.\node(sn9){P}; ] [.\node(sn10){NP}; ]]};
+   ([xshift=1.4em]cfrag3.south east) {\Tree[.\node(sn5){VP}; [.\node(sn6){VV}; 表示 ] [.\node(sn7){NN}; 担心 ]]};
 \end{scope}
 
-\begin{scope}[sibling distance=60pt]
+\begin{scope}[sibling distance=32pt,level distance=20pt]
 \node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag6) at
-   ([xshift=1.6em,yshift=0.5em]cfrag5.north west) {\Tree[.\node(sn11){VP}; [.\node(sn12){PP}; ] [.\node(sn13){VP}; ]]};
+   ([xshift=0.3em,yshift=4em]cfrag2.north west) {\Tree[.\node(sn11){VP}; [.\node(sn9){P}; ] [.\node(sn10){NP}; ] [.\node(sn13){VP}; ]]};
 \end{scope}
 
-\begin{scope}[sibling distance=80pt,level distance=18pt]
+\begin{scope}[sibling distance=65pt,level distance=18pt]
 \node[scale=0.8, inner sep=0.1cm,align=center,anchor=south east,draw] (cfrag7) at
-   ([xshift=-3.6em,yshift=0.5em]cfrag6.north east) {\Tree[.\node(sn14){IP}; [.\node(sn15){NP}; ] [.\node(sn16){VP}; ]]};
+   ([xshift=-4.5em,yshift=0.5em]cfrag6.north east) {\Tree[.\node(sn14){IP}; [.\node(sn15){NP}; ] [.\node(sn16){VP}; ]]};
 \end{scope}
 
 \node[scale=0.9,anchor=north,minimum size=18pt] (tw11) at ([xshift=-0.3em,yshift=-1.2em]cfrag1.south){he};
 \node[scale=0.9,anchor=west,minimum size=18pt] (tw12) at ([yshift=-0.1em,xshift=0.5em]tw11.east){was};
-\node[scale=0.9,anchor=west,minimum size=18pt] (tw13) at ([yshift=0.1em,xshift=0.5em]tw12.east){satisfied};
-\node[scale=0.9,anchor=west,minimum size=18pt] (tw14) at ([xshift=0.5em]tw13.east){with};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw13) at ([yshift=0.1em,xshift=0.5em]tw12.east){worried};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw14) at ([xshift=0.5em]tw13.east){about};
 \node[scale=0.9,anchor=west,minimum size=18pt] (tw15) at ([xshift=0.5em]tw14.east){the};
-\node[scale=0.9,anchor=west,minimum size=18pt] (tw16) at ([yshift=-0.1em,xshift=0.5em]tw15.east){answer};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw16) at ([yshift=-0.1em,xshift=0.5em]tw15.east){situation};
 
 \draw[dashed] ([xshift=-0.3em]cfrag1.south) -- ([yshift=-0.3em]tw11.north);
 \draw[dashed] (cfrag2.south) -- ([yshift=-0.4em]tw14.north);
@@ -228,40 +230,34 @@
 \draw[dashed] (cfrag3.south) -- ([yshift=-0.4em]tw16.north);
 \draw[dashed] (cfrag4.south) .. controls +(south:0.6) and +(north:0.6) .. ([yshift=-0.4em]tw13.north);
 
-\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag1.north) -- ([xshift=0.0em,yshift=10.0em]cfrag1.north);
-\draw[*-*] ([xshift=0.1em,yshift=-0.2em]cfrag2.north) -- ([xshift=0.1em,yshift=2.5em]cfrag2.north);
-\draw[*-*] ([xshift=0.1em,yshift=-0.4em]cfrag3.north) -- ([xshift=0.1em,yshift=0.7em]cfrag3.north);
-\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag4.north) -- ([xshift=0.0em,yshift=5.1em]cfrag4.north);
-\draw[*-*] ([xshift=0.1em,yshift=-0.2em]cfrag5.north) -- ([xshift=0.1em,yshift=0.9em]cfrag5.north);
-\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
-
 \visible<3->{
-\node [fill=blue,circle,inner sep=2pt] (rlabel1) at (cfrag1.south east) {{\color{white} \tiny{1}}};
-\draw[*-*,red,thick] ([xshift=0.0em,yshift=-0.2em]cfrag1.north) -- ([xshift=0.0em,yshift=10.0em]cfrag1.north);
-
-}
-\visible<5->{
-\node [fill=blue,circle,inner sep=2pt] (rlabel5) at (cfrag5.north west) {{\color{white} \tiny{5}}};
-\draw[*-*,red] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
+\draw[dashed,red] (cfrag2.south) -- ([yshift=-0.4em]tw14.north);
+\draw[dashed,red] (cfrag3.south) -- ([yshift=-0.4em]tw15.north);
+\draw[dashed,red] (cfrag3.south) -- ([yshift=-0.4em]tw16.north);
 }
+
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag1.north) -- ([xshift=0.0em,yshift=6.5em]cfrag1.north);
+\draw[*-*] ([xshift=-0.1em,yshift=-0.2em]cfrag2.north) -- ([xshift=-0.1em,yshift=4.4em]cfrag2.north);
+\draw[*-*] ([xshift=0.1em,yshift=-0.4em]cfrag3.north) .. controls +(north:2.4em) and +(south:2.4em) .. ([xshift=1.1em,yshift=2.5em]cfrag3.north);
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag4.north) -- ([xshift=0.0em,yshift=2.5em]cfrag4.north);
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
+
 \visible<4->{
-\node [fill=blue,circle,inner sep=2pt] (rlabel6) at (cfrag6.north east) {{\color{white} \tiny{6}}};
-\draw[*-*,red] ([xshift=0.1em,yshift=-0.2em]cfrag5.north) -- ([xshift=0.1em,yshift=0.9em]cfrag5.north);
-}
-\visible<3->{
-\node [fill=blue,circle,inner sep=2pt] (rlabel7) at (cfrag7.south west) {{\color{white} \tiny{7}}};
+\node [fill=blue,circle,inner sep=2pt] (rlabel2) at (cfrag2.north east) {{\color{white} \tiny{2}}};
+\node [fill=blue,circle,inner sep=2pt] (rlabel3) at (cfrag3.north east) {{\color{white} \tiny{3}}};
+\node [fill=blue,circle,inner sep=2pt] (rlabel6) at (cfrag6.north east) {{\color{white} \tiny{5}}};
 }
 
 \begin{pgfonlayer}{background}
-\visible<3->{
-\node [fill=green!20,inner sep=0pt] (cfrag1back) [fit = (cfrag1)] {};
-\node [fill=green!20,inner sep=0pt] (cfrag1back) [fit = (cfrag7)] {};
-}
 \visible<4->{
-\node [fill=green!20,inner sep=0pt] (cfrag1back) [fit = (cfrag6)] {};
+\node [fill=green!20,inner sep=0pt] (cfrag2back) [fit = (cfrag2)] {};
+\node [fill=green!20,inner sep=0pt] (cfrag3back) [fit = (cfrag3)] {};
+\node [fill=green!20,inner sep=0pt] (cfrag6back) [fit = (cfrag6)] {};
 }
-\visible<5->{
-\node [fill=green!20,inner sep=0pt] (cfrag1back) [fit = (cfrag5)] {};
+
+\visible<3->{
+\node [anchor=south west,draw=red,thick,fill=red!20,inner sep=0pt,minimum height = 2em, minimum width=6em] (ps) at ([xshift=-0.2em,yshift=-0.2em]cfrag2.south west) {};
+\node [anchor=south west,draw=red,thick,fill=red!20,inner sep=0pt] (pt) [fit = (tw14) (tw15) (tw16)] {};
 }
 \end{pgfonlayer}
 

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

@@ -2251,7 +2251,7 @@ d = r_1 \circ r_2 \circ r_3 \circ r_4
 
 \node[cnode,anchor=south,fill=red!30,align=left] (cat1) at ([xshift=-0.2em,yshift=2em]hiero.north west) {\footnotesize{基于形式文法}\\\footnotesize{的模型}};
 \node[cnode,anchor=south,fill=blue!30,align=left] (cat2) at ([xshift=-0.0em,yshift=2em]t2s.north) {\footnotesize{基于语言学}\\\footnotesize{句法的模型}};
-\node[cnode,anchor=south,minimum width=10.0em,fill=green!30,align=left] (cat0) at ([xshift=-3em,yshift=2em]cat2.north west) {\footnotesize{广义上基于}\\\footnotesize{句法的模型}};
+\node[cnode,anchor=south,minimum width=10.0em,fill=green!30,align=center] (cat0) at ([xshift=-3em,yshift=2em]cat2.north west) {\footnotesize{(广义上)}\\\footnotesize{基于句法的模型}};
 
 \draw [-,thick] ([yshift=0.1em,xshift=1em]cat1.north) -- ([xshift=-1.5em,yshift=-0.1em]cat0.south);
 \draw [-,thick] ([yshift=0.1em,xshift=-1em]cat2.north) -- ([xshift=1.5em,yshift=-0.1em]cat0.south);
@@ -3668,11 +3668,11 @@ NP(PN$_1$) $\to$ PN$_1$
 }
 \visible<5->{
 \node [fill=blue,circle,inner sep=2pt] (rlabel5) at (cfrag5.north west) {{\color{white} \tiny{5}}};
-\draw[*-*,red] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
+\draw[*-*,red] ([xshift=0.1em,yshift=-0.2em]cfrag5.north) -- ([xshift=0.1em,yshift=0.9em]cfrag5.north);
 }
 \visible<4->{
 \node [fill=blue,circle,inner sep=2pt] (rlabel6) at (cfrag6.north east) {{\color{white} \tiny{6}}};
-\draw[*-*,red] ([xshift=0.1em,yshift=-0.2em]cfrag5.north) -- ([xshift=0.1em,yshift=0.9em]cfrag5.north);
+\draw[*-*,red] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
 }
 \visible<3->{
 \node [fill=blue,circle,inner sep=2pt] (rlabel7) at (cfrag7.south west) {{\color{white} \tiny{7}}};
@@ -3700,6 +3700,131 @@ NP(PN$_1$) $\to$ PN$_1$
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
+%%%  SPMT规则
+\begin{frame}{更多的规则 - SPMT规则}
+\begin{itemize}
+\item 任意大小的规则都可以通过组合的方式获取，但是组合过多数量的规则会大大增加规则集大小。SPMT一种高效地获得大颗粒度规则的方法 (Marcu et al., 2006)
+	\begin{itemize}
+	\item 先抽取短语，之后找到覆盖这个短语的可信节点
+	\item 以这个可信节点做根，生成包含该短语的规则
+	\end{itemize}
+\end{itemize}
+
+\vspace{-0.3em}
+\begin{minipage}[b]{0.47\textwidth}
+{\footnotesize
+\visible<3->{
+对于任意一个与词对齐兼容的短语，可以找到包含它的``最小''翻译规则，即SPMT规则，比如\\
+
+\vspace{-0.4em}
+对 形式 $\to$ about the situation \\
+
+\vspace{-0.4em}
+可以很容易得到它的SPMT规则 \\
+
+\vspace{-0.4em}
+VP(P(对) NP(NN(局势)) VP$_1$) $\to$ VP$_1$ about the situation \\
+}
+
+\visible<4->{
+\vspace{-0.4em}
+但是，如果用组合的方式，需要三条最小规则才能得到这条规则\\
+}
+\vfill
+}
+\end{minipage}
+\hfill
+\begin{minipage}[t]{0.47\textwidth}
+\begin{tikzpicture}
+
+{\scriptsize
+\begin{scope}
+
+\visible<2->{
+\begin{scope}[level distance=20pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,draw] (cfrag1) at
+   (0,0.25) {\Tree[.\node(sn1){NP}; [.\node(sn2){PN}; 他 ]]};
+\end{scope}
+
+\begin{scope}[level distance=20pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag2) at
+   ([xshift=1.2em]cfrag1.south east) {\Tree[.\node(sn3){P}; 对 ]};
+\end{scope}
+
+\begin{scope}[level distance=20pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag3) at
+   ([xshift=1.2em]cfrag2.south east) {\Tree[.\node(sn4){NP}; [.NN 形式 ]]};
+   \end{scope}
+
+\begin{scope}[sibling distance=15pt,level distance=20pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag4) at
+   ([xshift=1.4em]cfrag3.south east) {\Tree[.\node(sn5){VP}; [.\node(sn6){VV}; 表示 ] [.\node(sn7){NN}; 担心 ]]};
+\end{scope}
+
+\begin{scope}[sibling distance=32pt,level distance=20pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south west,draw] (cfrag6) at
+   ([xshift=0.3em,yshift=4em]cfrag2.north west) {\Tree[.\node(sn11){VP}; [.\node(sn9){P}; ] [.\node(sn10){NP}; ] [.\node(sn13){VP}; ]]};
+\end{scope}
+
+\begin{scope}[sibling distance=65pt,level distance=18pt]
+\node[scale=0.8, inner sep=0.1cm,align=center,anchor=south east,draw] (cfrag7) at
+   ([xshift=-4.5em,yshift=0.5em]cfrag6.north east) {\Tree[.\node(sn14){IP}; [.\node(sn15){NP}; ] [.\node(sn16){VP}; ]]};
+\end{scope}
+
+\node[scale=0.9,anchor=north,minimum size=18pt] (tw11) at ([xshift=-0.3em,yshift=-1.2em]cfrag1.south){he};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw12) at ([yshift=-0.1em,xshift=0.5em]tw11.east){was};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw13) at ([yshift=0.1em,xshift=0.5em]tw12.east){worried};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw14) at ([xshift=0.5em]tw13.east){about};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw15) at ([xshift=0.5em]tw14.east){the};
+\node[scale=0.9,anchor=west,minimum size=18pt] (tw16) at ([yshift=-0.1em,xshift=0.5em]tw15.east){situation};
+
+\draw[dashed] ([xshift=-0.3em]cfrag1.south) -- ([yshift=-0.3em]tw11.north);
+\draw[dashed] (cfrag2.south) -- ([yshift=-0.4em]tw14.north);
+\draw[dashed] (cfrag3.south) -- ([yshift=-0.4em]tw15.north);
+\draw[dashed] (cfrag3.south) -- ([yshift=-0.4em]tw16.north);
+\draw[dashed] (cfrag4.south) .. controls +(south:0.6) and +(north:0.6) .. ([yshift=-0.4em]tw13.north);
+
+\visible<3->{
+\draw[dashed,red] (cfrag2.south) -- ([yshift=-0.4em]tw14.north);
+\draw[dashed,red] (cfrag3.south) -- ([yshift=-0.4em]tw15.north);
+\draw[dashed,red] (cfrag3.south) -- ([yshift=-0.4em]tw16.north);
+}
+
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag1.north) -- ([xshift=0.0em,yshift=6.5em]cfrag1.north);
+\draw[*-*] ([xshift=-0.1em,yshift=-0.2em]cfrag2.north) -- ([xshift=-0.1em,yshift=4.4em]cfrag2.north);
+\draw[*-*] ([xshift=0.1em,yshift=-0.4em]cfrag3.north) .. controls +(north:2.4em) and +(south:2.4em) .. ([xshift=1.1em,yshift=2.5em]cfrag3.north);
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag4.north) -- ([xshift=0.0em,yshift=2.5em]cfrag4.north);
+\draw[*-*] ([xshift=0.0em,yshift=-0.2em]cfrag6.north) -- ([xshift=0.0em,yshift=0.9em]cfrag6.north);
+
+\visible<4->{
+\node [fill=blue,circle,inner sep=2pt] (rlabel2) at (cfrag2.north east) {{\color{white} \tiny{2}}};
+\node [fill=blue,circle,inner sep=2pt] (rlabel3) at (cfrag3.north east) {{\color{white} \tiny{3}}};
+\node [fill=blue,circle,inner sep=2pt] (rlabel6) at (cfrag6.north east) {{\color{white} \tiny{5}}};
+}
+
+\begin{pgfonlayer}{background}
+\visible<4->{
+\node [fill=green!20,inner sep=0pt] (cfrag2back) [fit = (cfrag2)] {};
+\node [fill=green!20,inner sep=0pt] (cfrag3back) [fit = (cfrag3)] {};
+\node [fill=green!20,inner sep=0pt] (cfrag6back) [fit = (cfrag6)] {};
+}
+
+\visible<3->{
+\node [anchor=south west,draw=red,thick,fill=red!20,inner sep=0pt,minimum height = 2em, minimum width=6em] (ps) at ([xshift=-0.2em,yshift=-0.2em]cfrag2.south west) {};
+\node [anchor=south west,draw=red,thick,fill=red!20,inner sep=0pt] (pt) [fit = (tw14) (tw15) (tw16)] {};
+}
+\end{pgfonlayer}
+
+}
+\end{scope}
+}
+\end{tikzpicture}
+\end{minipage}
+
+\end{frame}
+
+
+%%%------------------------------------------------------------------------------------------------------------
 %%%  基于树结构的翻译文法 - 树到树
 \begin{frame}{树到树规则抽取}
 % 我的博士论文