Skip to content

T
Toy-MT-Introduction
Commit e881b370 by 孟霞
Options

合并分支 'master' 到 'mengxia' 

Master

查看合并请求 !131
parents 60bbc774 87a8c036
正在显示 包含 163 行增加 和 109 行删除
Book/Chapter4/chapter4.tex
...@@ -2322,7 +2322,7 @@ d_1 = {d'} \circ {r_5} ...@@ -2322,7 +2322,7 @@ d_1 = {d'} \circ {r_5}
\begin{itemize} \begin{itemize}
\vspace{0.5em} \vspace{0.5em}
\item 统计机器翻译的成功很大程度上来自判别式模型引入任意特征的能力。因此，在统计机器翻译时代，很多工作都集中在新特征的设计上。比如，可以基于不同的统计特征和先验知识设计翻译特征\cite{och2004smorgasbord,Chiang200911,gildea2003loosely}，也可以模仿分类任务设计大规模的稀疏特征\cite{chiang2008online}。另一方面，模型训练和特征权重调优也是统计机器翻译中的重要问题，除了最小错误率训练，还有很多方法。在过去十年，研究人员提出了许多有效的方法来学习现代SMT系统的特征值和权重，比如，最大似然估计\cite{koehn2003statistical,Peter1993The}、判别式方法\cite{Blunsom2008A}、贝叶斯方法\cite{Blunsom2009A,Cohn2009A}、最小风险训练\cite{smith2006minimum,li2009first-}、基于Margin的方法\cite{watanabe2007online,Chiang200911}以及基于排序模型的方法（PRO）\cite{Hopkins2011Tuning,dreyer2015apro}。实际上，统计机器翻译的训练和解码也存在不一致的问题，比如，特征值由双语数据上的极大似然估计得到（没有剪枝），而解码时却使用束剪枝，而且模型的目标是最大化机器翻译评价指标。对于这个问题也可以通过调整训练的目标函数进行缓解\cite{XiaoA,marcu2006practical}。 \item 统计机器翻译的成功很大程度上来自判别式模型引入任意特征的能力。因此，在统计机器翻译时代，很多工作都集中在新特征的设计上。比如，可以基于不同的统计特征和先验知识设计翻译特征\cite{och2004smorgasbord,Chiang200911,gildea2003loosely}，也可以模仿分类任务设计大规模的稀疏特征\cite{chiang2008online}。另一方面，模型训练和特征权重调优也是统计机器翻译中的重要问题，除了最小错误率训练，还有很多方法，比如，最大似然估计\cite{koehn2003statistical,Peter1993The}、判别式方法\cite{Blunsom2008A}、贝叶斯方法\cite{Blunsom2009A,Cohn2009A}、最小风险训练\cite{smith2006minimum,li2009first-}、基于Margin的方法\cite{watanabe2007online,Chiang200911}以及基于排序模型的方法（PRO）\cite{Hopkins2011Tuning,dreyer2015apro}。实际上，统计机器翻译的训练和解码也存在不一致的问题，比如，特征值由双语数据上的极大似然估计得到（没有剪枝），而解码时却使用束剪枝，而且模型的目标是最大化机器翻译评价指标。对于这个问题也可以通过调整训练的目标函数进行缓解\cite{XiaoA,marcu2006practical}。
\vspace{0.5em} \vspace{0.5em}
\item 统计机器翻译的另一个基础问题是如何表示并获取翻译单元（如短语）。传统方法中，研究者大多使用词对齐或者句法树等结构化信息，通过启发性方法进行短语和翻译规则的获取。不过这类方法最大的问题是上游系统（比如，词对齐、句法分析等）中的错误会影响到下游系统。因此，很多研究者尝试使用更多样的对齐或者句法分析来指导翻译单元的获取。比如，可以绕过词对齐，直接进行短语对齐\cite{denero2010phrase}；也可以使用多个句法树或者句法森林来覆盖更多的句法现象，进而增加规则抽取的召回率\cite{mi2008forest,xiao2010empirical}。另一个有趣的方向是用更紧凑的方式表示更多样的翻译假设，比如，直接将翻译结果用有限状态自动机表示，进行更大搜索空间上的解码\cite{de2010hierarchical,Casacuberta2004Machine}。 \item 统计机器翻译的另一个基础问题是如何表示并获取翻译单元（如短语）。传统方法中，研究者大多使用词对齐或者句法树等结构化信息，通过启发性方法进行短语和翻译规则的获取。不过这类方法最大的问题是上游系统（比如，词对齐、句法分析等）中的错误会影响到下游系统。因此，很多研究者尝试使用更多样的对齐或者句法分析来指导翻译单元的获取。比如，可以绕过词对齐，直接进行短语对齐\cite{denero2010phrase}；也可以使用多个句法树或者句法森林来覆盖更多的句法现象，进而增加规则抽取的召回率\cite{mi2008forest,xiao2010empirical}。另一个有趣的方向是用更紧凑的方式表示更多样的翻译假设，比如，直接将翻译结果用有限状态自动机表示，进行更大搜索空间上的解码\cite{de2010hierarchical,Casacuberta2004Machine}。
\vspace{0.5em} \vspace{0.5em}
......
Book/Chapter7/Chapter7.tex
This source diff could not be displayed because it is too large. You can view the blob instead.
Book/Chapter7/Figures/figure-batch-generation-method.tex
\begin{tikzpicture} \begin{tikzpicture}
\tikzstyle{node} = [minimum height=1.0em,draw=teal,fill=teal!10] \tikzstyle{node} = [minimum height=1.0*1.2em,draw=teal,fill=teal!10]
\tikzstyle{legend} = [minimum height=1.0em,minimum width=1.0em,draw] \tikzstyle{legend} = [minimum height=1.0*1.2em,minimum width=1.0*1.2em,draw]
\tikzstyle{node2} = [minimum width=1.0em,minimum height=4.1em,draw=blue,fill=blue!10] \tikzstyle{node2} = [minimum width=1.0*1.2em,minimum height=4.1*1.2em,draw=blue,fill=blue!10]
\node[node,minimum width=2.8em] (node1) at (0,0) {}; \node[node,minimum width=2.8*1.2em] (node1) at (0,0) {};
\node[node,minimum width=4.0em,anchor=north west] (node2) at (node1.south west) {}; \node[node,minimum width=4.0*1.2em,anchor=north west] (node2) at (node1.south west) {};
\node[node,minimum width=3.2em,anchor=north west] (node3) at (node2.south west) {}; \node[node,minimum width=3.2*1.2em,anchor=north west] (node3) at (node2.south west) {};
\node[node,minimum width=3.0em,anchor=north west] (node4) at (node3.south west) {}; \node[node,minimum width=3.0*1.2em,anchor=north west] (node4) at (node3.south west) {};
\node[node2,anchor = north west] (grad1) at ([xshift=1.2em]node1.north east) {}; \node[node2,anchor = north west] (grad1) at ([xshift=1.2em]node1.north east) {};
\node[node,minimum width=3.7em,anchor=north west] (node5) at (grad1.north east) {}; \node[node,minimum width=3.7*1.2em,anchor=north west] (node5) at (grad1.north east) {};
\node[node,minimum width=2.8em,anchor=north west] (node6) at (node5.south west) {}; \node[node,minimum width=2.8*1.2em,anchor=north west] (node6) at (node5.south west) {};
\node[node,minimum width=3.2em,anchor=north west] (node7) at (node6.south west) {}; \node[node,minimum width=3.2*1.2em,anchor=north west] (node7) at (node6.south west) {};
\node[node,minimum width=4.0em,anchor=north west] (node8) at (node7.south west) {}; \node[node,minimum width=4.0*1.2em,anchor=north west] (node8) at (node7.south west) {};
\node[font=\scriptsize,anchor=east] (line1) at (node1.west) {gpu1}; \node[font=\footnotesize,anchor=east] (line1) at (node1.west) {gpu1};
\node[font=\scriptsize,anchor=east] (line2) at (node2.west) {gpu2}; \node[font=\footnotesize,anchor=east] (line2) at (node2.west) {gpu2};
\node[font=\scriptsize,anchor=east] (line3) at (node3.west) {gpu3}; \node[font=\footnotesize,anchor=east] (line3) at (node3.west) {gpu3};
\node[font=\scriptsize,anchor=east] (line4) at (node4.west) {gpu4}; \node[font=\footnotesize,anchor=east] (line4) at (node4.west) {gpu4};
\node[node2,anchor = north west] (grad2) at ([xshift=0.3em]node5.north east) {}; \node[node2,anchor = north west] (grad2) at ([xshift=0.3em]node5.north east) {};
\draw[->] (-1.4em,-3.62em) -- (9.5em,-3.62em); \draw[->] (-1.4em*1.2,-3.62*1.2em) -- (9em*1.2,-3.62*1.2em);
\node[node,minimum width=2.8em] (node9) at (15em,0) {}; \node[node,minimum width=2.8*1.2em] (node9) at (16em,0) {};
\node[node,minimum width=4.0em,anchor=north west] (node10) at (node9.south west) {}; \node[node,minimum width=4.0*1.2em,anchor=north west] (node10) at (node9.south west) {};
\node[node,minimum width=3.2em,anchor=north west] (node11) at (node10.south west) {}; \node[node,minimum width=3.2*1.2em,anchor=north west] (node11) at (node10.south west) {};
\node[node,minimum width=3.0em,anchor=north west] (node12) at (node11.south west) {}; \node[node,minimum width=3.0*1.2em,anchor=north west] (node12) at (node11.south west) {};
\node[node,minimum width=3.7em,anchor=north west] (node13) at (node9.north east) {}; \node[node,minimum width=3.7*1.2em,anchor=north west] (node13) at (node9.north east) {};
\node[node,minimum width=2.8em,anchor=north west] (node14) at (node10.north east) {}; \node[node,minimum width=2.8*1.2em,anchor=north west] (node14) at (node10.north east) {};
\node[node,minimum width=3.2em,anchor=north west] (node15) at (node11.north east) {}; \node[node,minimum width=3.2*1.2em,anchor=north west] (node15) at (node11.north east) {};
\node[node,minimum width=4.0em,anchor=north west] (node16) at (node12.north east) {}; \node[node,minimum width=4.0*1.2em,anchor=north west] (node16) at (node12.north east) {};
\node[node2,anchor = north west] (grad3) at ([xshift=0.5em]node13.north east) {}; \node[node2,anchor = north west] (grad3) at ([xshift=0.5em]node13.north east) {};
\node[font=\scriptsize,anchor=east] (line1) at (node9.west) {gpu1}; \node[font=\footnotesize,anchor=east] (line1) at (node9.west) {gpu1};
\node[font=\scriptsize,anchor=east] (line2) at (node10.west) {gpu2}; \node[font=\footnotesize,anchor=east] (line2) at (node10.west) {gpu2};
\node[font=\scriptsize,anchor=east] (line3) at (node11.west) {gpu3}; \node[font=\footnotesize,anchor=east] (line3) at (node11.west) {gpu3};
\node[font=\scriptsize,anchor=east] (line4) at (node12.west) {gpu4}; \node[font=\footnotesize,anchor=east] (line4) at (node12.west) {gpu4};
\draw[->] (13.6em,-3.62em) -- (22.2em,-3.62em); \draw[->] (13.6*1.2em,-3.62*1.2em) -- (20.5*1.2em,-3.62*1.2em);
\begin{pgfonlayer}{background} \begin{pgfonlayer}{background}
\node [rectangle,inner sep=-0.0em,draw] [fit = (node1) (node2) (node3) (node4)] (box1) {}; \node [rectangle,inner sep=-0.0em,draw] [fit = (node1) (node2) (node3) (node4)] (box1) {};
\node [rectangle,inner sep=-0.0em,draw] [fit = (node5) (node6) (node7) (node8)] (box2) {}; \node [rectangle,inner sep=-0.0em,draw] [fit = (node5) (node6) (node7) (node8)] (box2) {};
\node [rectangle,inner sep=-0.0em,draw] [fit = (node9) (node13) (node12) (node16)] (box2) {}; \node [rectangle,inner sep=-0.0em,draw] [fit = (node9) (node13) (node12) (node16)] (box2) {};
\end{pgfonlayer} \end{pgfonlayer}
\node[font=\scriptsize,anchor=north] (legend1) at ([xshift=3em]node4.south) {一步一更新}; \node[font=\footnotesize,anchor=north] (legend1) at ([xshift=3em]node4.south) {一步一更新};
\node[font=\scriptsize,anchor=north] (legend2) at ([xshift=2.5em]node12.south) {累积两步更新}; \node[font=\footnotesize,anchor=north] (legend2) at ([xshift=2.5em]node12.south) {累积两步更新};
\node[font=\scriptsize,anchor=north] (time1) at (grad2.south) {time}; \node[font=\footnotesize,anchor=north] (time1) at (grad2.south) {time};
\node[font=\scriptsize,anchor=north] (time1) at (grad3.south) {time}; \node[font=\footnotesize,anchor=north] (time1) at (grad3.south) {time};
\node[legend] (legend3) at (2em,2em) {}; \node[legend] (legend3) at (2em,2em) {};
\node[font=\scriptsize,anchor=west] (idle) at (legend3.east) {:空闲}; \node[font=\footnotesize,anchor=west] (idle) at (legend3.east) {:空闲};
\node[legend,anchor=west,draw=teal,fill=teal!10] (legend4) at ([xshift = 2em]idle.east) {}; \node[legend,anchor=west,draw=teal,fill=teal!10] (legend4) at ([xshift = 2em]idle.east) {};
\node[font=\scriptsize,anchor=west] (FB) at (legend4.east) {:前向/反向}; \node[font=\footnotesize,anchor=west] (FB) at (legend4.east) {:前向/反向};
\node[legend,anchor=west,draw=blue,fill=blue!10] (legend5) at ([xshift = 2em]FB.east) {}; \node[legend,anchor=west,draw=blue,fill=blue!10] (legend5) at ([xshift = 2em]FB.east) {};
\node[font=\scriptsize,anchor=west] (grad_sync) at (legend5.east) {:梯度更新}; \node[font=\footnotesize,anchor=west] (grad_sync) at (legend5.east) {:梯度更新};
\end{tikzpicture} \end{tikzpicture}
\ No newline at end of file
Book/Chapter7/Figures/figure-randomly-generation-vs-generate-by-sentence-length.tex
\begin{tikzpicture} \begin{tikzpicture}
\tikzstyle{node} = [minimum height=1.0em,draw=teal,fill=teal!10] \tikzstyle{node} = [minimum height=1.0*1.2em,draw=teal,fill=teal!10]
\node[node,minimum width=2.0em] (sent1) at (0,0) {}; \node[node,minimum width=2.0*1.2em] (sent1) at (0,0) {};
\node[node,minimum width=5.0em,anchor=north west] (sent2) at (sent1.south west) {}; \node[node,minimum width=5.0*1.2em,anchor=north west] (sent2) at (sent1.south west) {};
\node[node,minimum width=1.0em,anchor=north west] (sent3) at (sent2.south west) {}; \node[node,minimum width=1.0*1.2em,anchor=north west] (sent3) at (sent2.south west) {};
\node[node,minimum width=3.0em,anchor=north west] (sent4) at (sent3.south west) {}; \node[node,minimum width=3.0*1.2em,anchor=north west] (sent4) at (sent3.south west) {};
\node[node,minimum width=4.0em] (sent5) at (12em,0) {}; \node[node,minimum width=4.0*1.2em] (sent5) at (14em,0) {};
\node[node,minimum width=4.5em,anchor=north west] (sent6) at (sent5.south west) {}; \node[node,minimum width=4.5*1.2em,anchor=north west] (sent6) at (sent5.south west) {};
\node[node,minimum width=4.5em,anchor=north west] (sent7) at (sent6.south west) {}; \node[node,minimum width=4.5*1.2em,anchor=north west] (sent7) at (sent6.south west) {};
\node[node,minimum width=5em,anchor=north west] (sent8) at (sent7.south west) {}; \node[node,minimum width=5*1.2em,anchor=north west] (sent8) at (sent7.south west) {};
\node[font=\scriptsize,anchor=east] (line1) at (sent1.west) {sent1}; \node[font=\footnotesize,anchor=east] (line1) at (sent1.west) {sent1};
\node[font=\scriptsize,anchor=east] (line2) at (sent2.west) {sent2}; \node[font=\footnotesize,anchor=east] (line2) at (sent2.west) {sent2};
\node[font=\scriptsize,anchor=east] (line3) at (sent3.west) {sent3}; \node[font=\footnotesize,anchor=east] (line3) at (sent3.west) {sent3};
\node[font=\scriptsize,anchor=east] (line4) at (sent4.west) {sent4}; \node[font=\footnotesize,anchor=east] (line4) at (sent4.west) {sent4};
\node[font=\scriptsize,anchor=east] (line5) at (sent5.west) {sent1}; \node[font=\footnotesize,anchor=east] (line5) at (sent5.west) {sent1};
\node[font=\scriptsize,anchor=east] (line6) at (sent6.west) {sent2}; \node[font=\footnotesize,anchor=east] (line6) at (sent6.west) {sent2};
\node[font=\scriptsize,anchor=east] (line7) at (sent7.west) {sent3}; \node[font=\footnotesize,anchor=east] (line7) at (sent7.west) {sent3};
\node[font=\scriptsize,anchor=east] (line8) at (sent8.west) {sent4}; \node[font=\footnotesize,anchor=east] (line8) at (sent8.west) {sent4};
\begin{pgfonlayer}{background} \begin{pgfonlayer}{background}
\node [rectangle,inner sep=-0.0em,draw] [fit = (sent1) (sent2) (sent3) (sent4)] (box1) {}; \node [rectangle,inner sep=-0.0em,draw] [fit = (sent1) (sent2) (sent3) (sent4)] (box1) {};
\node [rectangle,inner sep=-0.0em,draw] [fit = (sent5) (sent6) (sent7) (sent8)] (box2) {}; \node [rectangle,inner sep=-0.0em,draw] [fit = (sent5) (sent6) (sent7) (sent8)] (box2) {};
\end{pgfonlayer} \end{pgfonlayer}
\node[font=\scriptsize] (node1) at ([yshift=-3em]sent2.south) {随机生成}; \node[font=\footnotesize] (node1) at ([yshift=-3.4em]sent2.south) {随机生成};
\node[font=\scriptsize] (node2) at ([yshift=-1em]sent8.south) {排序生成}; \node[font=\footnotesize] (node2) at ([yshift=-1em]sent8.south) {排序生成};
\end{tikzpicture} \end{tikzpicture}
\ No newline at end of file
Book/Chapter7/Figures/figure-word-change.tex
\begin{center} \begin{center}
\centerline{以英语为例：}
\vspace{0.5em}
\begin{tikzpicture} \begin{tikzpicture}
\node[rounded corners=3pt,minimum width=10.0em,minimum height=2.0em,draw,thick,fill=green!5,font=\scriptsize,drop shadow,inner sep=0.5em] (left) at (0,0) { \node[rounded corners=3pt,minimum width=10.0em,minimum height=2.0em,draw,thick,fill=green!5,font=\scriptsize,drop shadow,inner sep=0.5em] (left) at (0,0) {
\begin{tabular}{c} \begin{tabular}{c}
......
Book/mt-book-xelatex.idx
\indexentry{流畅度|hyperpage}{12} \indexentry{组合性翻译|hyperpage}{10}
\indexentry{Fluency|hyperpage}{12} \indexentry{Compositional Translation|hyperpage}{10}
\indexentry{准确性|hyperpage}{12} \indexentry{短语|hyperpage}{10}
\indexentry{Accuracy|hyperpage}{12} \indexentry{短语切分|hyperpage}{15}
\indexentry{充分性|hyperpage}{12} \indexentry{Phrasal Segmentation|hyperpage}{15}
\indexentry{Adequacy|hyperpage}{12} \indexentry{短语对|hyperpage}{15}
\indexentry{翻译候选|hyperpage}{13} \indexentry{推导|hyperpage}{15}
\indexentry{Translation Candidate|hyperpage}{13} \indexentry{Derivation|hyperpage}{15}
\indexentry{训练|hyperpage}{15} \indexentry{生成式模型|hyperpage}{18}
\indexentry{Training|hyperpage}{15} \indexentry{Generative Model|hyperpage}{18}
\indexentry{解码|hyperpage}{15} \indexentry{判别式模型|hyperpage}{18}
\indexentry{Decoding|hyperpage}{15} \indexentry{Discriminative Model|hyperpage}{18}
\indexentry{推断|hyperpage}{15} \indexentry{对数线性模型|hyperpage}{19}
\indexentry{Inference|hyperpage}{15} \indexentry{Log-linear Model|hyperpage}{19}
\indexentry{词对齐|hyperpage}{20} \indexentry{短语抽取|hyperpage}{20}
\indexentry{Word Alignment|hyperpage}{20} \indexentry{Phrase Extraction|hyperpage}{20}
\indexentry{词对齐连接|hyperpage}{20} \indexentry{词汇化翻译概率|hyperpage}{23}
\indexentry{解码|hyperpage}{23} \indexentry{Lexical Translation Probability|hyperpage}{23}
\indexentry{Decoding|hyperpage}{23} \indexentry{短语表|hyperpage}{23}
\indexentry{噪声信道模型|hyperpage}{26} \indexentry{Phrase Table|hyperpage}{23}
\indexentry{Noise Channel Model|hyperpage}{26} \indexentry{调序|hyperpage}{24}
\indexentry{词对齐|hyperpage}{29} \indexentry{Reordering|hyperpage}{24}
\indexentry{Word Alignment|hyperpage}{29} \indexentry{模型训练|hyperpage}{28}
\indexentry{非对称的词对齐|hyperpage}{29} \indexentry{Model Training|hyperpage}{28}
\indexentry{Asymmetric Word Alignment|hyperpage}{29} \indexentry{权重调优|hyperpage}{28}
\indexentry{空对齐|hyperpage}{29} \indexentry{Weight Tuning|hyperpage}{28}
\indexentry{拉格朗日乘数法|hyperpage}{37} \indexentry{最小错误率训练|hyperpage}{28}
\indexentry{The Lagrange Multiplier Method|hyperpage}{37} \indexentry{Minimum Error Rate Training|hyperpage}{28}
\indexentry{期望最大化|hyperpage}{40} \indexentry{调优集合|hyperpage}{28}
\indexentry{Expectation Maximization|hyperpage}{40} \indexentry{Tuning Set|hyperpage}{28}
\indexentry{期望频次|hyperpage}{40} \indexentry{线搜索|hyperpage}{29}
\indexentry{Expected Count|hyperpage}{41} \indexentry{Line Search|hyperpage}{29}
\indexentry{产出率|hyperpage}{44} \indexentry{格搜索|hyperpage}{30}
\indexentry{繁衍率|hyperpage}{44} \indexentry{Grid Search|hyperpage}{30}
\indexentry{Fertility|hyperpage}{44} \indexentry{覆盖度模型|hyperpage}{32}
\indexentry{扭曲度|hyperpage}{46} \indexentry{Coverage Model|hyperpage}{32}
\indexentry{Distortion|hyperpage}{46} \indexentry{翻译候选|hyperpage}{32}
\indexentry{概念单元|hyperpage}{48} \indexentry{Translation Candidate|hyperpage}{32}
\indexentry{概念|hyperpage}{48} \indexentry{翻译假设|hyperpage}{33}
\indexentry{Concept|hyperpage}{48} \indexentry{Translation Hypothesis|hyperpage}{33}
\indexentry{缺陷|hyperpage}{49} \indexentry{剪枝|hyperpage}{34}
\indexentry{Deficiency|hyperpage}{49} \indexentry{Pruning|hyperpage}{34}
\indexentry{凸函数|hyperpage}{54} \indexentry{束剪枝|hyperpage}{34}
\indexentry{Convex function|hyperpage}{54} \indexentry{Beam Pruning|hyperpage}{34}
\indexentry{对称化|hyperpage}{55} \indexentry{直方图剪枝|hyperpage}{34}
\indexentry{Symmetrization|hyperpage}{55} \indexentry{Histogram Pruning|hyperpage}{34}
\indexentry{系统偏置|hyperpage}{56} \indexentry{阈值剪枝|hyperpage}{34}
\indexentry{System Bias|hyperpage}{56} \indexentry{Threshold Pruning|hyperpage}{34}
\indexentry{假设重组|hyperpage}{34}
\indexentry{Hypothesis Recombination|hyperpage}{34}
\indexentry{基于层次短语的模型|hyperpage}{38}
\indexentry{Hierarchical Phrase-based Model|hyperpage}{38}
\indexentry{同步上下文无关文法|hyperpage}{39}
\indexentry{Synchronous Context-free Grammar|hyperpage}{39}
\indexentry{基于层次短语的文法|hyperpage}{40}
\indexentry{Hierarchical Phrase-based Grammar|hyperpage}{40}
\indexentry{推导|hyperpage}{41}
\indexentry{Derivation|hyperpage}{41}
\indexentry{胶水规则|hyperpage}{41}
\indexentry{Glue Rule|hyperpage}{41}
\indexentry{乔姆斯基范式|hyperpage}{45}
\indexentry{Chomsky Normal Form|hyperpage}{45}
\indexentry{跨度|hyperpage}{45}
\indexentry{Span|hyperpage}{45}
\indexentry{自下而上的分析|hyperpage}{46}
\indexentry{Top-down Parsing|hyperpage}{46}
\indexentry{束剪枝|hyperpage}{48}
\indexentry{Beam Pruning|hyperpage}{48}
\indexentry{立方剪枝|hyperpage}{50}
\indexentry{Cube Pruning|hyperpage}{50}
\indexentry{序列化|hyperpage}{53}
\indexentry{线性化|hyperpage}{53}
\indexentry{Linearization|hyperpage}{53}
\indexentry{树到串翻译规则|hyperpage}{55}
\indexentry{Tree-to-String Translation Rule|hyperpage}{55}
\indexentry{树到树翻译规则|hyperpage}{55}
\indexentry{Tree-to-Tree Translation Rule|hyperpage}{55}
\indexentry{树片段|hyperpage}{56}
\indexentry{Tree Fragment|hyperpage}{56}
\indexentry{同步树替换文法规则|hyperpage}{57}
\indexentry{Synchronous Tree Substitution Grammar Rule|hyperpage}{57}
\indexentry{边缘集合|hyperpage}{63}
\indexentry{Frontier Set|hyperpage}{63}
\indexentry{最小规则|hyperpage}{64}
\indexentry{Minimal Rules|hyperpage}{64}
\indexentry{二叉化|hyperpage}{67}
\indexentry{Binarization|hyperpage}{67}
\indexentry{基于短语的特征|hyperpage}{72}
\indexentry{基于句法的特征|hyperpage}{72}
\indexentry{有向超图|hyperpage}{73}
\indexentry{Directed Hyper-graph|hyperpage}{73}
\indexentry{超边|hyperpage}{73}
\indexentry{Hyper-edge|hyperpage}{73}
\indexentry{半环分析|hyperpage}{73}
\indexentry{Semi-ring Parsing|hyperpage}{73}
\indexentry{组合|hyperpage}{75}
\indexentry{Composition|hyperpage}{75}
\indexentry{基于串的解码|hyperpage}{76}
\indexentry{String-based Decoding|hyperpage}{76}
\indexentry{基于树的解码|hyperpage}{76}
\indexentry{Tree-based Decoding|hyperpage}{76}
\indexentry{Lexicalized Norm Form|hyperpage}{79}
Book/mt-book-xelatex.tex
...@@ -98,7 +98,7 @@ ...@@ -98,7 +98,7 @@
{\large {\large
\noindent {\color{red} 在此感谢所有为本书做出贡献的人} \\ \noindent {\color{red} 在此感谢所有为本书做出贡献的人} \\
\noindent 曹润柘、曾信、孟霞、单韦乔、姜雨帆、王子扬、刘辉、许诺、李北、刘继强、张哲旸、周书含、周涛、张裕浩、李炎洋、林野、刘晓倩、牛蕊、田丰宁、杜权、陈贺轩 \\ \noindent 曹润柘、曾信、孟霞、单韦乔、姜雨帆、王子扬、刘辉、许诺、李北、刘继强、张哲旸、周书含、周涛、张裕浩、李炎洋、林野、陈贺轩、刘晓倩、牛蕊、田丰宁、杜权 \\
} }
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
...@@ -125,10 +125,10 @@ ...@@ -125,10 +125,10 @@
%\include{Chapter1/chapter1} %\include{Chapter1/chapter1}
%\include{Chapter2/chapter2} %\include{Chapter2/chapter2}
%\include{Chapter3/chapter3} %\include{Chapter3/chapter3}
%\include{Chapter4/chapter4} \include{Chapter4/chapter4}
%\include{Chapter5/chapter5} %\include{Chapter5/chapter5}
%\include{Chapter6/chapter6} %\include{Chapter6/chapter6}
\include{Chapter7/chapter7} %\include{Chapter7/chapter7}
%\include{ChapterAppend/chapterappend} %\include{ChapterAppend/chapterappend}
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论