updates

54fa983b · xiaotong · 8cd65e1f · 54fa983b · 54fa983b · 54fa983b
Commit 54fa983b authored Jan 05, 2020 by xiaotong
--- a/Section04-Phrasal-and-Syntactic-Models/section04-test.tex
+++ b/Section04-Phrasal-and-Syntactic-Models/section04-test.tex
@@ -152,35 +152,60 @@
 \subsection{规则匹配}
 %%%------------------------------------------------------------------------------------------------------------
-%%%  基于树的解码 vs 基于串的解码
+%%%  基于树的解码方法 - 超图
-\begin{frame}{基于树的解码 vs 基于串的解码}
+\begin{frame}{基于树的解码 - 超图}
 \begin{itemize}
-\item 前面的公式本质上描述了一种基于串的解码，即对输入的源语言句子通过句法模型进行翻译，得到译文串。不过，搜索所有的推导导致巨大的解码空间。对于树到串和树到树翻译来说，源语言句法树是可见的，因此可以使用另一种解码方法 - 基于树的解码，即把输出入的源语句法树翻译为目标语串\\
+\item 如果源语言输入的是句法树，基于树的解码会找到一个推导覆盖整个句法树，之后输出所对应的目标语词串作为译文
+\item 比如，可以从树的叶子结点开始，找到所有能匹配到这个节点的规则，当所有节点匹配完之后，本质上获得了一个超图
+	\begin{itemize}
+	\item<2-> 图的节点对应一个句法树句法节点
+	\item<2-> 图的边(或者叫超边)对应规则，边的头指向规则左部(源语言端)所对应图节点，边可以有多个尾，每个尾对应规则右部(源语言端)中的一个变量
+	\end{itemize}
 \end{itemize}
-\centering
+\visible<2->{
-\begin{tabular} {l | l l}
+\begin{center}
-\textbf{对比} & \textbf{基于树的解码} & \textbf{基于串的解码} \\ \hline
+\begin{tikzpicture}
-解码方法 &
+{\scriptsize
-\parbox{0.35\textwidth}{
+\begin{scope}[sibling distance=5pt, level distance=20pt]
-\begin{equation}
+\Tree[.\node(cn1){VP$^{[1]}$};
-\hat{d} = \argmax_{d \in D_{\textrm{tree}}} \textrm{score}(d) \nonumber
+        [.\node(cn2){AD$^{[2]}$}; 大幅度 ]
-\end{equation}
+        [.\node(cn3){VP$^{[3]}$};
+            [.\node(cn4){VV$^{[4]}$}; 下降 ]
+            [.\node(cn5){AS$^{[5]}$}; 了 ]
+        ]
+     ]
+\node [anchor=south] (treelabel) at (cn1.north) {\scriptsize{源语句法树}};
+\end{scope}
+\begin{scope}[xshift=1.3in,sibling distance=5pt, level distance=20pt]
+\Tree[.\node(sn1){VP};  [.\node(sn2){AD}; \node(sw1){大幅度}; ] [.\node(sn3){VP};] ]
+\node [anchor=south] (rulelabel) at ([yshift=0.2em,xshift=4em]sn1.north) {\scriptsize{匹配的翻译规则}};
+\end{scope}
+\draw [->,thick] (sn3.east) -- ([xshift=1em]sn3.east);
+\node [anchor=west] (rr) at ([xshift=1em]sn3.east) {drastically VP};
+\node [anchor=west,circle,draw,inner sep=2pt] (tail) at ([yshift=-3em,xshift=3em]rr.south east) {\tiny{[3]}};
+\node [anchor=west,circle,draw,inner sep=2pt] (head) at ([yshift=2.5em,xshift=5em]rr.south east) {\tiny{[1]}};
+\draw [-latex,thick] ([yshift=0.1em]tail.60) -- ([yshift=-0.1em]head.260);
+\node [anchor=north] (headlabel) at ([xshift=0.5em]head.south) {\tiny{头}};
+\node [anchor=west] (taillabel) at ([yshift=1.2em,xshift=-0.3em]tail.east) {\tiny{尾}};
+\node [anchor=south] (graphlabel) at ([yshift=0.6em]head.north) {\scriptsize{超图}};
+\begin{pgfonlayer}{background}
+\node [fill=green!20,inner sep=2pt,drop shadow] (rulebox) [fit = (sn1) (sn2) (sn3) (sw1) (rr)] {};
+\draw [->,dotted,thick] ([yshift=2em]rulebox.east) ..controls +(east:3.5em) and +(west:1.5em).. ([yshift=1em,xshift=0.3em]tail.north);
+\node [fill=red!20,inner sep=0pt] (nodebox1) [fit = (cn1)] {};
+\node [fill=red!20,inner sep=0pt] (nodebox2) [fit = (sn1)] {};
+\draw [<->,red] (nodebox1) edge [out=15, in=160] (nodebox2);
+\end{pgfonlayer}
 }
-& 
-\parbox{0.35\textwidth}{
+\end{tikzpicture}
-\begin{equation}
+\end{center}
-\hat{d} = \argmax_{d \in D} \textrm{score}(d) \nonumber
-\end{equation}
 }
-\\ \hline
-搜索空间 & 与输入的源语句法树 & 所有推导$D$ \\
-         & 兼容的推导$D_{\textrm{tree}}$ & \\ \hline
-适用模型 & 树到串、树到树 & 所有句法模型 \\ \hline
-解码算法 & CYK + 规则二叉化 & chart解码 \\ \hline
-速度 & 快 & 一般较慢 
-\end{tabular}
 \end{frame}

--- a/Section04-Phrasal-and-Syntactic-Models/section04.tex
+++ b/Section04-Phrasal-and-Syntactic-Models/section04.tex
@@ -4085,6 +4085,7 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 \end{minipage}
 \begin{minipage}[c][5cm][t]{0.50\textwidth}
 \visible<2->{
+\renewcommand*{\arraystretch}{0.95}
 \begin{tabular}{l l}
 \multicolumn{2}{l}{\textbf{\scriptsize{抽取得到的规则}}} \\
 \hline
@@ -4095,11 +4096,13 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 \scriptsize{$r_5$} & \scriptsize{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$} \\
 \multicolumn{2}{l}{\tiny{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}} \\
 \end{tabular}
+\renewcommand*{\arraystretch}{1.0}
 }
 \visible<3->{
 \vspace{0.5em}
+\renewcommand*{\arraystretch}{0.95}
 \begin{tabular}{l l}
 \multicolumn{2}{l}{\textbf{\scriptsize{无法得到的规则}}} \\
 \hline
@@ -4108,6 +4111,7 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
                     & \scriptsize{NP(DT(the) NNS(imports))} \\
 \scriptsize{$r_{?}$} & \scriptsize{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)} \\
 \end{tabular}
+\renewcommand*{\arraystretch}{1.0}
 }
 \end{minipage}
@@ -4215,6 +4219,7 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 \end{minipage}
 \begin{minipage}[c][5cm][t]{0.50\textwidth}
 \only<1>{
+\renewcommand*{\arraystretch}{0.9}
 \begin{tabular}{l l}
 \multicolumn{2}{l}{\textbf{\scriptsize{抽取得到的规则(词对齐)}}} \\
 \hline
@@ -4225,9 +4230,11 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 \scriptsize{$r_5$} & \scriptsize{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$} \\
 \multicolumn{2}{l}{\tiny{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}} \\
 \end{tabular}
+\renewcommand*{\arraystretch}{1.0}
 }
 \visible<4->{
+\renewcommand*{\arraystretch}{0.9}
 \begin{tabular}{l l}
 \multicolumn{2}{l}{\textbf{\scriptsize{抽取得到的规则(子树对齐)}}} \\
 \hline
@@ -4244,6 +4251,7 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
                           & \alert{\scriptsize{VP(VBZ$_3$ ADVP(RB$_1$ VBN$_2$)}} \\
 \alert{\scriptsize{$r_9$}} & \alert{\scriptsize{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)}} \\
 \end{tabular}
+\renewcommand*{\arraystretch}{1.0}
 }
 \end{minipage}
@@ -4418,7 +4426,7 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 \end{frame}
 %%%------------------------------------------------------------------------------------------------------------
-\subsection{规则匹配}
+\subsection{基于树结构的解码}
 %%%------------------------------------------------------------------------------------------------------------
 %%%  解码模型
@@ -4466,13 +4474,71 @@ NP-BAR(NN$_1$ NP-BAR$_2$) $\to$ NN$_1$ NP-BAR$_2$
 搜索空间 & 与输入的源语句法树 & 所有推导$D$ \\
         & 兼容的推导$D_{\textrm{tree}}$ & \\ \hline
 适用模型 & 树到串、树到树 & 所有句法模型 \\ \hline
-解码算法 & CYK + 规则二叉化 & chart解码 \\ \hline
+解码算法 & chart解码 &  CYK + 规则二叉化 \\ \hline
 速度 & 快 & 一般较慢
 \end{tabular}
 \end{frame}
+%%%------------------------------------------------------------------------------------------------------------
+%%%  基于树的解码方法 - 超图
+\begin{frame}{基于树的解码 - 超图}
+\begin{itemize}
+\item 如果源语言输入的是句法树，基于树的解码会找到一个推导覆盖整个句法树，之后输出所对应的目标语词串作为译文
+\item 比如，可以从树的叶子结点开始，找到所有能匹配到这个节点的规则，当所有节点匹配完之后，本质上获得了一个超图
+	\begin{itemize}
+	\item<2-> 图的节点对应一个句法树句法节点
+	\item<2-> 图的边(或者叫超边)对应规则，边的头指向规则左部(源语言端)所对应图节点，边可以有多个尾，每个尾对应规则右部(源语言端)中的一个变量
+	\end{itemize}
+\end{itemize}
+\visible<2->{
+\begin{center}
+\begin{tikzpicture}
+{\scriptsize
+\begin{scope}[sibling distance=5pt, level distance=20pt]
+\Tree[.\node(cn1){VP$^{[1]}$};
+        [.\node(cn2){AD$^{[2]}$}; 大幅度 ]
+        [.\node(cn3){VP$^{[3]}$};
+            [.\node(cn4){VV$^{[4]}$}; 下降 ]
+            [.\node(cn5){AS$^{[5]}$}; 了 ]
+        ]
+     ]
+\node [anchor=south] (treelabel) at (cn1.north) {\scriptsize{源语句法树}};
+\end{scope}
+\begin{scope}[xshift=1.3in,sibling distance=5pt, level distance=20pt]
+\Tree[.\node(sn1){VP};  [.\node(sn2){AD}; \node(sw1){大幅度}; ] [.\node(sn3){VP};] ]
+\node [anchor=south] (rulelabel) at ([yshift=0.2em,xshift=4em]sn1.north) {\scriptsize{匹配的翻译规则}};
+\end{scope}
+\draw [->,thick] (sn3.east) -- ([xshift=1em]sn3.east);
+\node [anchor=west] (rr) at ([xshift=1em]sn3.east) {drastically VP};
+\node [anchor=west,circle,draw,inner sep=2pt] (tail) at ([yshift=-3em,xshift=3em]rr.south east) {\tiny{[3]}};
+\node [anchor=west,circle,draw,inner sep=2pt] (head) at ([yshift=2.5em,xshift=5em]rr.south east) {\tiny{[1]}};
+\draw [-latex,thick] ([yshift=0.1em]tail.60) -- ([yshift=-0.1em]head.260);
+\node [anchor=north] (headlabel) at ([xshift=0.5em]head.south) {\tiny{头}};
+\node [anchor=west] (taillabel) at ([yshift=1.2em,xshift=-0.3em]tail.east) {\tiny{尾}};
+\node [anchor=south] (graphlabel) at ([yshift=0.6em]head.north) {\scriptsize{超图}};
+\begin{pgfonlayer}{background}
+\node [fill=green!20,inner sep=2pt,drop shadow] (rulebox) [fit = (sn1) (sn2) (sn3) (sw1) (rr)] {};
+\draw [->,dotted,thick] ([yshift=2em]rulebox.east) ..controls +(east:3.5em) and +(west:1.5em).. ([yshift=1em,xshift=0.3em]tail.north);
+\node [fill=red!20,inner sep=0pt] (nodebox1) [fit = (cn1)] {};
+\node [fill=red!20,inner sep=0pt] (nodebox2) [fit = (sn1)] {};
+\draw [<->,red] (nodebox1) edge [out=15, in=160] (nodebox2);
+\end{pgfonlayer}
+}
+\end{tikzpicture}
+\end{center}
+}
+\end{frame}
 %%%------------------------------------------------------------------------------------------------------------
 %%%  基于串的解码

--- a/Section06-Neural-Machine-Translation/section06.tex
+++ b/Section06-Neural-Machine-Translation/section06.tex
@@ -2565,7 +2565,7 @@ $\textrm{``you''} = \argmax_{y} \textrm{P}(y|\textbf{s}_1, \alert{\textbf{C}})$ 
                xtick={0,1,2},
                xticklabels={纽约时报,发表,评论},
                xticklabel style={rotate=45,anchor=south west,font=\scriptsize,inner sep=0pt,outer sep=2pt},
-                xtick pos=upper,xticklabel pos=upper,
+                xticklabel pos=upper,
                colormap={bluewhite}{color=(white) color=(blue)},
            ]
                \addplot3[matrix plot] file [meta=index 2] {Figures/example1.dat};
@@ -2586,7 +2586,7 @@ $\textrm{``you''} = \argmax_{y} \textrm{P}(y|\textbf{s}_1, \alert{\textbf{C}})$ 
                xtick={0,1,2,3},
                xticklabels={我,来到,这个,世界},
                xticklabel style={rotate=45,anchor=south west,font=\scriptsize,inner sep=0pt,outer sep=2pt},
-                xtick pos=upper,xticklabel pos=upper,
+                xticklabel pos=upper,
                colormap={bluewhite}{color=(white) color=(blue)},
                colorbar,
                colorbar style={