合并分支 'caorunzhe' 到 'master'

Caorunzhe

查看合并请求 !283

Book/Chapter3/chapter3.tex

@@ -37,7 +37,7 @@
 %    NEW SECTION
 %----------------------------------------------------------------------------------------
 
-\section{词在翻译中的作用}
+\section{什么是基于词的翻译模型}
 
 \parinterval 在机器翻译中，我们希望得到一个源语言到目标语言的翻译。对于人类来说这个问题很简单，但是让计算机做这样的工作却很困难，因为我们需要把翻译``描述''成计算机可以计算的形式。这里面临的第一个问题是：如何对翻译进行建模？从计算机的角度来看，这就需要把自然语言的翻译问题转换为计算机可计算的问题。
 
@@ -82,7 +82,7 @@
 %----------------------------------------------------------------------------------------
 
 \sectionnewpage
-\section{一个简单的翻译系统}
+\section{构建一个简单的机器翻译系统}
 \label{sec:simple-mt-example}
 
 \parinterval 本节首先对比人工翻译和机器翻译过程的异同点，从中归纳出构建机器翻译系统的两个主要步骤：训练和解码。之后，会从学习翻译知识和运用翻译知识两个方面描述如何构建一个简单的机器翻译系统。

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

@@ -2,7 +2,7 @@
 % !TEX encoding = UTF-8 Unicode
 
 \def\CTeXPreproc{Created by ctex v0.2.13, don't edit!}
-\documentclass[cjk,t,compress,12pt]{beamer}
+\documentclass[CJKutf8,t,compress,12pt]{beamer}
 \usepackage{pstricks}
 \usepackage{etex}
 \usepackage{eso-pic,graphicx}
@@ -10,7 +10,7 @@
 \usepackage{amsmath,amssymb}
 \usepackage{setspace}
 \usepackage{xcolor}
-\usepackage{CJK}
+\usepackage{CJKutf8}
 \usepackage{tikz}
 \usepackage{tikz-qtree}
 \usepackage{hyperref}
@@ -1187,21 +1187,21 @@ $d$是一个$(\textbf{s},\textbf{t})$上基于短语的翻译推导，$\textrm{P
 \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];
+\tikzstyle{datanode} = [minimum width=7em,minimum height=1.7em,fill=blue!20,rounded corners=0.7em];
+\tikzstyle{modelnode} = [minimum width=7em,minimum height=1.7em,fill=red!20,rounded corners=0.2em];
+\tikzstyle{decodingnode} = [minimum width=7em,minimum height=1.7em,fill=green!20,rounded corners=0.2em];
 
-\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 [datanode,anchor=north west] (bitext) at (0,0) {{ \scriptsize{训练用双语数据}}};
+\node [modelnode,anchor=north] (phrase) at ([yshift=-1.5em]bitext.south) {{ \scriptsize{短语抽取及打分}}};
+\node [modelnode,anchor=west] (reorder) at ([xshift=1.5em]phrase.east) {{ \scriptsize{调序建模}}};
+\node [modelnode,anchor=west] (lm) at ([xshift=1.5em]reorder.east) {{ \scriptsize{语言建模}}};
+\node [datanode,anchor=south] (monotext) at ([yshift=1.5em]lm.north) {{ \scriptsize{目标语单语数据}}};
 
-\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 [datanode,anchor=north] (phrasetable) at ([yshift=-1.5em]phrase.south) {{ \scriptsize{短语表}}};
+\node [datanode,anchor=north] (reordertable) at ([yshift=-1.5em]reorder.south) {{ \scriptsize{调序模型}}};
+\node [datanode,anchor=north] (lmtable) at ([yshift=-1.5em]lm.south) {{ \scriptsize{语言模型}}};
 
-\node [decodingnode,anchor=north] (decoding) at ([yshift=-2em]reordertable.south) {{\color{white} \scriptsize{解码器}}};
+\node [decodingnode,anchor=north] (decoding) at ([yshift=-2em]reordertable.south) {{ \scriptsize{解码器}}};
 
 \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);
@@ -3466,22 +3466,22 @@ d = r_1 \circ r_2 \circ r_3 \circ r_4
 \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];
-
-\node [datanode,anchor=north west] (bitext) at (0,0) {{\color{white} \scriptsize{训练用双语数据}}};
-\node [modelnode, anchor=north west] (gi) at ([xshift=2em,yshift=-0.2em]bitext.south east) {{\color{white} \scriptsize{文法(规则)抽取}}};
-\node [datanode,anchor=north east] (birules) at ([xshift=-2em,yshift=-0.2em]gi.south west) {{\color{white} \scriptsize{同步翻译文法}}};
-\node [modelnode, anchor=north west] (training) at ([xshift=2em,yshift=-0.2em]birules.south east) {{\color{white} \scriptsize{特征值学习}}};
-\node [datanode,anchor=north east] (model) at ([xshift=-2em,yshift=-0.2em]training.south west) {{\color{white} \scriptsize{翻译模型}}};
-\node [decodingnode, anchor=north west] (tuning) at ([xshift=2em,yshift=-0.2em]model.south east) {{\color{white} \scriptsize{特征权重调优}}};
-\node [datanode,anchor=north east] (tuningdata) at ([xshift=-2em,yshift=-0.2em]tuning.south west) {{\color{white} \scriptsize{调优用双语数据}}};
-\node [decodingnode, anchor=north west] (decoding) at ([xshift=2em,yshift=-0.2em]tuningdata.south east) {{\color{white} \scriptsize{解码新句子}}};
-
-\node [datanode,anchor=south west] (monotext) at ([xshift=2em,yshift=0.2em]training.north east) {{\color{white} \scriptsize{目标语数据}}};
-\node [modelnode,anchor=south west] (lm) at ([xshift=2em,yshift=0.2em]tuning.north east) {{\color{white} \scriptsize{$n$-gram语言建模}}};
-\node [datanode,anchor=south west] (lmmodel) at ([xshift=2em,yshift=0.2em]decoding.north east) {{\color{white} \scriptsize{语言模型}}};
+\tikzstyle{datanode} = [minimum width=7em,minimum height=1.7em,fill=blue!20,rounded corners=0.7em];
+\tikzstyle{modelnode} = [minimum width=7em,minimum height=1.7em,fill=red!20,rounded corners=0.2em];
+\tikzstyle{decodingnode} = [minimum width=7em,minimum height=1.7em,fill=green!20,rounded corners=0.2em];
+
+\node [datanode,anchor=north west] (bitext) at (0,0) {{ \scriptsize{训练用双语数据}}};
+\node [modelnode, anchor=north west] (gi) at ([xshift=2em,yshift=-0.2em]bitext.south east) {{ \scriptsize{文法(规则)抽取}}};
+\node [datanode,anchor=north east] (birules) at ([xshift=-2em,yshift=-0.2em]gi.south west) {{ \scriptsize{同步翻译文法}}};
+\node [modelnode, anchor=north west] (training) at ([xshift=2em,yshift=-0.2em]birules.south east) {{ \scriptsize{特征值学习}}};
+\node [datanode,anchor=north east] (model) at ([xshift=-2em,yshift=-0.2em]training.south west) {{ \scriptsize{翻译模型}}};
+\node [decodingnode, anchor=north west] (tuning) at ([xshift=2em,yshift=-0.2em]model.south east) {{ \scriptsize{特征权重调优}}};
+\node [datanode,anchor=north east] (tuningdata) at ([xshift=-2em,yshift=-0.2em]tuning.south west) {{ \scriptsize{调优用双语数据}}};
+\node [decodingnode, anchor=north west] (decoding) at ([xshift=2em,yshift=-0.2em]tuningdata.south east) {{ \scriptsize{解码新句子}}};
+
+\node [datanode,anchor=south west] (monotext) at ([xshift=2em,yshift=0.2em]training.north east) {{ \scriptsize{目标语数据}}};
+\node [modelnode,anchor=south west] (lm) at ([xshift=2em,yshift=0.2em]tuning.north east) {{ \scriptsize{$n$-gram语言建模}}};
+\node [datanode,anchor=south west] (lmmodel) at ([xshift=2em,yshift=0.2em]decoding.north east) {{ \scriptsize{语言模型}}};
 
 \draw [->,very thick] ([yshift=-0.3em,xshift=0.1em]bitext.east) -- ([yshift=0.1em]gi.north west);
 \draw [->,very thick] ([yshift=-0.1em]gi.south west) -- ([yshift=0.3em,xshift=0.1em]birules.east);

Section05-Neural-Networks-and-Language-Modeling/section05.tex

@@ -2,7 +2,7 @@
 % !TEX encoding = UTF-8 Unicode
 
 \def\CTeXPreproc{Created by ctex v0.2.13, don't edit!}
-\documentclass[cjk,t,compress,12pt]{beamer}
+\documentclass[CJKutf8,t,compress,12pt]{beamer}
 \usepackage{pstricks}
 \usepackage{etex}
 \usepackage{eso-pic,graphicx}
@@ -11,7 +11,7 @@
 \usepackage{setspace}
 \usepackage{xcolor}
 \usepackage{array,multirow}
-\usepackage{CJK}
+\usepackage{CJKutf8}
 \usepackage{tikz}
 \usepackage{tikz-qtree}
 \usepackage{hyperref}

Section06-Neural-Machine-Translation/section06.tex

@@ -2,7 +2,7 @@
 % !TEX encoding = UTF-8 Unicode
 
 \def\CTeXPreproc{Created by ctex v0.2.13, don't edit!}
-\documentclass[cjk,t,compress,12pt]{beamer}
+\documentclass[CJKutf8,t,compress,12pt]{beamer}
 \usepackage{pstricks}
 \usepackage{etex}
 \usepackage{eso-pic,graphicx}
@@ -11,7 +11,7 @@
 \usepackage{setspace}
 \usepackage{xcolor}
 \usepackage{array,multirow}
-\usepackage{CJK}
+\usepackage{CJKutf8}
 \usepackage{tikz}
 \usepackage{tikz-qtree}
 \usepackage{hyperref}