update

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

+% !Mode:: "TeX:UTF-8"
+% !TEX encoding = UTF-8 Unicode
+
+\def\CTeXPreproc{Created by ctex v0.2.13, don't edit!}
+\documentclass[cjk,t,compress,12pt]{beamer}
+\usepackage{pstricks}
+\usepackage{etex}
+\usepackage{eso-pic,graphicx}
+\usepackage{fancybox}
+\usepackage{amsmath,amssymb}
+\usepackage{setspace}
+\usepackage{xcolor}
+\usepackage{CJK}
+\usepackage{tikz}
+\usepackage{tikz-qtree}
+\usepackage{hyperref}
+\usepackage{ulem}
+
+\usepackage{tcolorbox}
+\tcbuselibrary{skins}
+
+\usetikzlibrary{calc,intersections}
+\usetikzlibrary{matrix}
+\usetikzlibrary{patterns}
+\usetikzlibrary{arrows,decorations.pathreplacing}
+\usetikzlibrary{shadows} 
+\usetikzlibrary{shadows.blur}
+\usepgflibrary{arrows}
+\usetikzlibrary{arrows}
+\usetikzlibrary{decorations}
+\usetikzlibrary{arrows,shapes}
+
+\usetikzlibrary{positioning,fit,calc}
+
+\usetikzlibrary{mindmap,backgrounds} % mind map
+
+\DeclareMathOperator*{\argmax}{arg\,max}
+\DeclareMathOperator*{\argmin}{arg\,min}
+
+\setbeamertemplate{items}[ball]
+\usefonttheme[onlymath]{serif} 
+
+\definecolor{ugreen}{rgb}{0,0.5,0}
+\definecolor{lgreen}{rgb}{0.9,1,0.8}
+\definecolor{xtgreen1}{rgb}{0.824,0.898,0.8}
+\definecolor{xtgreen}{rgb}{0.914,0.945,0.902}
+\definecolor{lightgray}{gray}{0.85}
+
+\setbeamercolor{uppercol}{fg=white,bg=ugreen}
+\setbeamercolor{lowercol}{fg=black,bg=xtgreen}
+
+%\definecolor{ublue}{rgb}{0,0.298,0.525}
+\definecolor{ublue}{rgb}{0.152,0.250,0.545}
+\setbeamercolor{uppercolblue}{fg=white,bg=ublue}
+\setbeamercolor{lowercolblue}{fg=black,bg=blue!10}
+
+\usefonttheme[onlylarge]{structurebold}
+
+\IfFileExists{C:/WINDOWS/win.ini}
+{\newcommand{\mycfont}{you}}
+{\newcommand{\mycfont}{gbsn}}
+
+\begin{CJK}{UTF8}{\mycfont}
+\end{CJK}
+
+\setbeamerfont*{frametitle}{size=\large,series=\bfseries}
+\setbeamertemplate{navigation symbols}{\begin{CJK}{UTF8}{\mycfont} 第四章 基于短语和句法的翻译模型 \hspace*{2em} 肖桐\&朱靖波 \end{CJK} \hspace*{2em} \today \hspace*{2em} \insertframenumber{}/\inserttotalframenumber}
+
+\setbeamertemplate{itemize items}[circle] % if you want a circle
+\setbeamertemplate{itemize subitem}[triangle] % if you want a triangle
+\setbeamertemplate{itemize subsubitem}[ball] % if you want a ball
+
+\begin{document}
+
+\begin{CJK}{UTF8}{\mycfont}
+
+\title{\Large{基于短语和句法的翻译模型}}
+\author{\large{\textbf{肖桐\ \ 朱靖波}}}
+\institute{
+\blue{\url{xiaotong@mail.neu.edu.cn}} \black{} \\
+\blue{\url{zhujingbo@mail.neu.edu.cn}} \black{} \\
+\vspace{1.0em}
+东北大学 自然语言处理实验室 \\
+\blue{\underline{\url{http://www.nlplab.com}}} \black{} \\
+\vspace{0.2cm}
+\hspace{0.1cm} \includegraphics[scale=0.1]{../Figures/logo.pdf}
+}
+\date{}
+
+\maketitle
+
+\setlength{\leftmargini}{1em}
+\setlength{\leftmarginii}{1em}
+
+%%%------------------------------------------------------------------------------------------------------------
+\section{使用更大的翻译单元}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 短语 -> 句法
+\begin{frame}{使用短语就够了？}
+
+\begin{itemize}
+\item 短语是具有完整意思的连续词串，因此可以捕捉更多的上下文信息
+	\begin{itemize}
+	\item 不过过大的短语也会造成问题，比如数据稀疏
+	\item 而且单纯的词串也缺乏句法功能表示能力
+	\end{itemize}
+\item 另一种方式是考虑句子的句法结构
+\end{itemize}
+
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 基于句法的模型
+\begin{frame}{引入句法信息}
+\begin{itemize}
+\item 句法树是句子的更高层次的抽象，相比短语句法树具有更加丰富的句法功能标记，对语言结构的转换很有帮助
+	\begin{itemize}
+	\item 更容易捕捉翻译中的远距离调序
+	\item 使用句法更容易对大范围的上下文建模
+	\end{itemize}
+\end{itemize}
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% 本章的内容
+\begin{frame}{Outline}
+
+ \begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=red!5!white,colframe=red!75!black,drop fuzzy shadow]
+{\normalsize
+\textbf{基于短语的模型} \vspace{-0.2em}\\
+\small{1. 建模} \vspace{-0.2em}\\
+\small{2. 如何获取短语} \vspace{-0.2em}\\
+\small{3. 判别式模型和最小错误率训练} \vspace{-0.2em}\\
+\small{4. 栈解码}
+}
+\end{tcolorbox}
+
+\vspace{0em}
+
+ \begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=red!5!white,colframe=red!75!black,drop fuzzy shadow]
+{\normalsize
+\textbf{基于层次短语的模型} \vspace{-0.2em}\\
+\small{1. 同步上下文无关文法} \vspace{-0.2em}\\
+\small{2. 层次短语规则及特征} \vspace{-0.2em}\\
+\small{3. 基于chart的解码和立方剪枝}
+}
+\end{tcolorbox}
+
+\vspace{0em}
+
+\begin{tcolorbox}[enhanced,size=normal,left=2mm,right=1mm,colback=red!5!white,colframe=red!75!black,drop fuzzy shadow]
+{\normalsize
+\textbf{基于语言学句法的模型} \vspace{-0.2em}\\
+\small{1. 基于树结构的文法} \vspace{-0.2em}\\
+\small{2. 翻译规则抽取} \vspace{-0.2em}\\
+\small{3. 规则匹配}
+}
+\end{tcolorbox}
+
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+\section{基于短语的模型}
+
+%%%------------------------------------------------------------------------------------------------------------
+\section{基于层次短语的模型}
+
+%%%------------------------------------------------------------------------------------------------------------
+\section{基于语言学句法的模型}
+
+\end{CJK}
+\end{document}

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

@@ -97,7 +97,7 @@
 \setlength{\leftmarginii}{1em}
 
 %%%------------------------------------------------------------------------------------------------------------
-\section{翻译中为什么要使用短语}
+\section{使用更大的翻译单元}
 
 %%%------------------------------------------------------------------------------------------------------------
 %%% 基于单词的模型的问题
@@ -160,9 +160,9 @@
 
 \vspace{0.5em}
 
-\item<3-> 基于单词的翻译模型有哪些\alert{缺点}？
+\item<3-> 基于单词的翻译模型有哪些\alert{不足}？
     \begin{itemize}
-    \item 很多 - 这符合中国人的思维，缺点总是很多 :)
+    \item 需要定义词是什么
     \item 独立性假设：单词之间相对独立，没有考虑搭配
     \item 调序：较弱的调序建模
     \item ...
@@ -234,7 +234,7 @@
 \begin{frame}{引入更大的翻译单元}
 
 \begin{itemize}
-\item 简单的单词翻译似乎不行，咋办？\visible<2->{\alert{- 引入更大的翻译单元}}
+\item 简单的单词翻译似乎不行？\visible<2->{\alert{- 引入更大的翻译单元}}
 
     \begin{minipage}[t]{0.40\linewidth}
     \begin{center}
@@ -293,7 +293,7 @@
     \end{scope}
 
     \visible<3->{
-    \begin{scope}[yshift=-6em]
+    \begin{scope}[yshift=-5.0em]
     \begin{scope}
     {\footnotesize
     \node [anchor=west] (s1) at (0,0) {我};
@@ -334,7 +334,7 @@
     \end{center}
     \end{minipage}
 
-\item<4-> \alert{优点}很多
+\item<4-> \alert{优点}：
     \begin{itemize}
     \item 翻译时候可以考虑更大范围的上下文信息\\
           比如："红茶"中的"红"如果和"茶"搭配 ...
@@ -521,7 +521,7 @@
 
 %%%------------------------------------------------------------------------------------------------------------
 %%% 基于短语的翻译模型
-\begin{frame}{基于"短语"的机器翻译}
+\begin{frame}{基于``短语''的机器翻译}
 
 \begin{itemize}
 \item 对每个\alert{单词}及\alert{连续词串}的翻译进行（任意）组合
@@ -687,5 +687,11 @@
 
 \end{frame}
 
+%%%------------------------------------------------------------------------------------------------------------
+\section{基于短语的模型}
+
+%%%------------------------------------------------------------------------------------------------------------
+\section{基于句法的模型}
+
 \end{CJK}
 \end{document}

Section06-Neural-Machine-Translation/section06.tex

@@ -30,23 +30,22 @@
 \usetikzlibrary{matrix}
 \usetikzlibrary{patterns}
 \usetikzlibrary{arrows,decorations.pathreplacing}
-\usetikzlibrary{shadows} % LATEX and plain TEX when using Tik Z
+\usetikzlibrary{shadows} 
 \usetikzlibrary{shadows.blur}
-
-\usepgflibrary{arrows} % LATEX and plain TEX and pure pgf
-\usetikzlibrary{arrows} % LATEX and plain TEX when using Tik Z
+\usepgflibrary{arrows}
+\usetikzlibrary{arrows}
 \usetikzlibrary{decorations}
 \usetikzlibrary{arrows,shapes}
 
 \usetikzlibrary{positioning,fit,calc}
 
-\usetikzlibrary{mindmap,backgrounds} % mind map
+\usetikzlibrary{mindmap,backgrounds}
 
 \DeclareMathOperator*{\argmax}{arg\,max}
 \DeclareMathOperator*{\argmin}{arg\,min}
 
 \setbeamertemplate{items}[ball]
-\usefonttheme[onlymath]{serif}  % fout of math
+\usefonttheme[onlymath]{serif} 
 
 \definecolor{ugreen}{rgb}{0,0.5,0}
 \definecolor{lgreen}{rgb}{0.9,1,0.8}