updates

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

@@ -146,130 +146,99 @@
 \subsection{翻译规则抽取}
 
 %%%------------------------------------------------------------------------------------------------------------
-%%%  SPMT规则
-\begin{frame}{更多的规则 - SPMT规则}
+%%%  tree binarization
+\begin{frame}{更多的规则 - 句法树二叉化}
 \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)
+\item 句法分析器生成的句法树可能会非常平坦，这会导致抽取的规则很``大''而且规则无法继续被分解
 	\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
+	\item 比如，在CTB中经常会看到很宽的子树结构
 	\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{center}
 \begin{tikzpicture}
 
 {\scriptsize
-\begin{scope}
+\begin{scope}[scale = 0.9, sibling distance=20pt, level distance=30pt]
 
-\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 ]};
+{\footnotesize
+\Tree[.IP
+     	[.NP ]
+     	[.VP ]
+        [., ]
+        [.VP ]
+        [., ]
+        [.VP ]
+        [., ]
+        [.VP ]
+        [.{.{\color{white} V}} ]
+     ]
+}
 \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}
+\end{tikzpicture}
+\end{center}
 
-\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{itemize}
+\item<2-> 一个具体的例子
+\end{itemize}
 
-\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}
+\vspace{-1.0em}
+\begin{center}
+\begin{tikzpicture}
 
-\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}
+\visible<2->{
+{\scriptsize
+\begin{scope}[sibling distance=4pt, level distance=25pt]
 
-\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);
+{\footnotesize
+\Tree[.\node(n1){NP};
+     	[.NNP \node(sw1){美国}; ]
+     	[.NN \node(sw2){总统}; ]
+        [.NN \node(sw3){唐纳德}; ]
+        [.NN \node(sw4){特朗普}; ]
+     ]
 }
 
-\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);
+\node [anchor=north] (tw1) at ([yshift=-2em]sw1.south) {U.S.};
+\node [anchor=north] (tw2) at ([yshift=-2em]sw2.south) {President};
+\node [anchor=north] (tw3) at ([yshift=-2em]sw3.south) {Trump};
 
-\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}}};
-}
+\draw [-,dashed] (sw1.south) -- (tw1.north);
+\draw [-] (sw2.south) -- (tw2.north);
+\draw [-] (sw3.south) -- (tw3.north);
+\draw [-] (sw4.south) -- (tw3.north);
 
-\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)] {};
-}
+\node [anchor=west] (rulelabel1) at ([xshift=1in,yshift=0em]n1.east) {\footnotesize{\textbf{抽取到的规则：}}};
+\node [anchor=north west] (rule1) at (rulelabel1.south west) {NP(NNP$_1$ NN$_2$ NN(唐纳德) NN(特朗普))};
+\node [anchor=north west] (rule1t) at ([yshift=0.2em]rule1.south west) {$\to$ NNP$_1$ NN$_2$ Trump};
+\node [anchor=north west] (rule2) at (rule1t.south west) {NP(NNP$_1$ NN(总统) NN(唐纳德) NN(特朗普))};
+\node [anchor=north west] (rule2t) at ([yshift=0.2em]rule2.south west) {$\to$ NNP$_1$ President Trump};
+\node [anchor=north west] (rulelabel2) at (rule2t.south west) {\footnotesize{\textbf{\alert{不能}抽取到的规则：}}};
+\node [anchor=north west] (rule3) at (rulelabel2.south west) {NP(NN(唐纳德) NN(特朗普)) $\to$ Trump};
 
-\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{center}
 
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------
+%%%  tree binarization (cont.)
+\begin{frame}{更多的规则 - 句法树二叉化(续)}
+\begin{itemize}
+\item 句法分析器生成的句法树可能会非常平坦，这会导致抽取的规则很``大''而且规则无法继续被分解
+	\begin{itemize}
+	\item 比如，在CTB中经常会看到很宽的子树结构
+	\end{itemize}
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
 \subsection{规则匹配}
 
 \end{CJK}

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

@@ -3727,7 +3727,7 @@ VP(P(对) NP(NN(局势)) VP$_1$) $\to$ VP$_1$ about the situation \\
 }
 
 \visible<4->{
-\vspace{-0.4em}
+\vspace{-0.3em}
 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