Skip to content

T
Toy-MT-Introduction
Commit 74a81006 by 曹润柘
Options

update bib

parent abe862a0
正在显示 包含 59 行增加 和 57 行删除
Book/Chapter1/chapter1.tex
...@@ -536,7 +536,7 @@ His house is on the south bank of the river. ...@@ -536,7 +536,7 @@ His house is on the south bank of the river.
\begin{itemize} \begin{itemize}
\item GroundHog：GroundHog\cite{bahdanau2015neural}基于Theano\cite{al2016theano}框架，由蒙特利尔大学LISA 实验室使用Python语言编写的一个框架，旨在提供灵活而高效的方式来实现复杂的循环神经网络模型。它提供了包括LSTM在内的多种模型。Bahdanau等人在此框架上又编写了GroundHog神经机器翻译系统。该系统也作为了很多论文的基线系统。网址：\url{https://github.com/lisa-groundhog/GroundHog} \item GroundHog：GroundHog\cite{bahdanau2015neural}基于Theano\cite{al2016theano}框架，由蒙特利尔大学LISA 实验室使用Python语言编写的一个框架，旨在提供灵活而高效的方式来实现复杂的循环神经网络模型。它提供了包括LSTM在内的多种模型。Bahdanau等人在此框架上又编写了GroundHog神经机器翻译系统。该系统也作为了很多论文的基线系统。网址：\url{https://github.com/lisa-groundhog/GroundHog}
\vspace{0.5em} \vspace{0.5em}
\item Nematus：Nematus\cite{SennrichNematus}是英国爱丁堡大学开发的，基于Theano框架的神经机器翻译系统。该系统使用GRU作为隐层单元，支持多层网络。Nematus 编码端有正向和反向的编码方式，可以同时提取源语句子中的上下文信息。该系统的一个优点是，它可以支持输入端有多个特征的输入（例如词的词性等）。网址：\url{https://github.com/EdinburghNLP/nematus} \item Nematus：Nematus\cite{DBLP:journals/corr/SennrichFCBHHJL17}是英国爱丁堡大学开发的，基于Theano框架的神经机器翻译系统。该系统使用GRU作为隐层单元，支持多层网络。Nematus 编码端有正向和反向的编码方式，可以同时提取源语句子中的上下文信息。该系统的一个优点是，它可以支持输入端有多个特征的输入（例如词的词性等）。网址：\url{https://github.com/EdinburghNLP/nematus}
\vspace{0.5em} \vspace{0.5em}
\item ZophRNN：ZophRNN\cite{zoph2016simple}是由南加州大学的Barret Zoph 等人使用C++语言开发的系统。Zoph既可以训练序列表示模型（如语言模型），也可以训练序列到序列的模型（如神经机器翻译模型）。当训练神经机器翻译系统时，ZophRNN也支持多源输入。网址：\url{https://github.com/isi-nlp/Zoph\_RNN} \item ZophRNN：ZophRNN\cite{zoph2016simple}是由南加州大学的Barret Zoph 等人使用C++语言开发的系统。Zoph既可以训练序列表示模型（如语言模型），也可以训练序列到序列的模型（如神经机器翻译模型）。当训练神经机器翻译系统时，ZophRNN也支持多源输入。网址：\url{https://github.com/isi-nlp/Zoph\_RNN}
\vspace{0.5em} \vspace{0.5em}
...@@ -558,7 +558,7 @@ His house is on the south bank of the river. ...@@ -558,7 +558,7 @@ His house is on the south bank of the river.
\vspace{0.5em} \vspace{0.5em}
\item CytonMT：由NICT开发的一种用C++实现的神经机器翻译开源工具包\cite{WangCytonMT}。主要支持Transformer模型，并支持一些常用的训练方法以及解码方法。网址：\url{https://github.com/arthurxlw/cytonMt} \item CytonMT：由NICT开发的一种用C++实现的神经机器翻译开源工具包\cite{WangCytonMT}。主要支持Transformer模型，并支持一些常用的训练方法以及解码方法。网址：\url{https://github.com/arthurxlw/cytonMt}
\vspace{0.5em} \vspace{0.5em}
\item OpenSeq2Seq：由NVIDIA团队开发的\cite{KuchaievMixed}基于Tensorflow的模块化架构，用于序列到序列的模型，允许从可用组件中组装新模型，支持混合精度训练，利用NVIDIA Volta Turing GPU中的Tensor核心，基于Horovod的快速分布式训练，支持多GPU，多节点多模式。网址：\url{https://nvidia.github.io/OpenSeq2Seq/html/index.html} \item OpenSeq2Seq：由NVIDIA团队开发的\cite{DBLP:journals/corr/abs-1805-10387}基于Tensorflow的模块化架构，用于序列到序列的模型，允许从可用组件中组装新模型，支持混合精度训练，利用NVIDIA Volta Turing GPU中的Tensor核心，基于Horovod的快速分布式训练，支持多GPU，多节点多模式。网址：\url{https://nvidia.github.io/OpenSeq2Seq/html/index.html}
\vspace{0.5em} \vspace{0.5em}
\item NMTPyTorch：由勒芒大学语言实验室发布的基于序列到序列框架的神经网络翻译系统\cite{nmtpy2017}，Nmtpytorch的核心部分依赖于Numpy，Pytorch和tqdm。其允许训练各种端到端神经体系结构，包括但不限于神经机器翻译，图像字幕和自动语音识别系统。网址：\url{https://github.com/lium-lst/nmtpytorch} \item NMTPyTorch：由勒芒大学语言实验室发布的基于序列到序列框架的神经网络翻译系统\cite{nmtpy2017}，Nmtpytorch的核心部分依赖于Numpy，Pytorch和tqdm。其允许训练各种端到端神经体系结构，包括但不限于神经机器翻译，图像字幕和自动语音识别系统。网址：\url{https://github.com/lium-lst/nmtpytorch}
\end{itemize} \end{itemize}
......
Book/Chapter4/Figures/combine-minimum-rule-1.tex
%%%------------------------------------------------------------------------------------------------------------ %%%------------------------------------------------------------------------------------------------------------
%%% 组合规则 %%% 组合规则
\begin{minipage}[b]{0.42\textwidth} \begin{minipage}[b]{0.38\textwidth}
{\small {\footnotesize
\renewcommand*{\arraystretch}{1.3} \renewcommand*{\arraystretch}{1.3}
\begin{tabular}{l l} \begin{tabular}{l l}
{$r_1$} & {NP(PN(他)) $\to$ he} \\ {$r_1$} & {NP(PN(他)) $\to$ he} \\
......
Book/Chapter4/Figures/minimum-rule-from-tree-cutting-1.tex
%%%------------------------------------------------------------------------------------------------------------ %%%------------------------------------------------------------------------------------------------------------
%%% 最小规则 %%% 最小规则
\begin{minipage}[b]{0.38\textwidth} \begin{minipage}[b]{0.35\textwidth}
{\small {\footnotesize
\renewcommand*{\arraystretch}{1.3} \renewcommand*{\arraystretch}{1.3}
\begin{tabular}{l l} \begin{tabular}{l l}
{$r_1$} & {NP(PN(他)) $\to$ he} \\ {$r_1$} & {NP(PN(他)) $\to$ he} \\
......
Book/Chapter4/Figures/tree-binarization.tex
...@@ -4,7 +4,7 @@ ...@@ -4,7 +4,7 @@
\begin{tikzpicture} \begin{tikzpicture}
{ {
{\small {\scriptsize
\begin{scope}[sibling distance=4pt, level distance=25pt] \begin{scope}[sibling distance=4pt, level distance=25pt]
{\footnotesize {\footnotesize
...@@ -25,12 +25,12 @@ ...@@ -25,12 +25,12 @@
\draw [-,dashed] (sw3.south) -- (tw3.north); \draw [-,dashed] (sw3.south) -- (tw3.north);
\draw [-,dashed] (sw4.south) -- (tw3.north); \draw [-,dashed] (sw4.south) -- (tw3.north);
\node [anchor=west] (rulelabel1) at ([xshift=1in,yshift=0.3em]n1.east) {{抽取到的规则：}}; \node [anchor=west] (rulelabel1) at ([xshift=1in,yshift=0.3em]n1.east) {\footnotesize{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] (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] (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] (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] (rule2t) at ([yshift=0.2em]rule2.south west) {$\to$ NNP$_1$ President Trump};
\node [anchor=north west] (rulelabel2) at ([yshift=-0.3em]rule2t.south west) {{{\red{不能}}抽取到的规则：}}; \node [anchor=north west] (rulelabel2) at ([yshift=-0.3em]rule2t.south west) {\footnotesize{{\red{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}; \node [anchor=north west] (rule3) at (rulelabel2.south west) {NP(NN(唐纳德) NN(特朗普)) $\to$ Trump};
\end{scope} \end{scope}
......
Book/Chapter4/Figures/tree-to-string-rule-empty-alignment-1.tex
%%%------------------------------------------------------------------------------------------------------------ %%%------------------------------------------------------------------------------------------------------------
%%% 处理空对其单词 %%% 处理空对其单词
\begin{minipage}[b]{0.38\textwidth} \begin{minipage}[b]{0.35\textwidth}
{\small {\footnotesize
\renewcommand*{\arraystretch}{1.3} \renewcommand*{\arraystretch}{1.3}
\begin{tabular}{l l} \begin{tabular}{l l}
{$r_1$} & {NP(PN(他)) $\to$ he} \\ {$r_1$} & {NP(PN(他)) $\to$ he} \\
......
Book/Chapter4/Figures/tree-to-tree-rule-extraction-base-node-alignment.tex
...@@ -48,31 +48,31 @@ ...@@ -48,31 +48,31 @@
\end{scope} \end{scope}
\node[anchor=north](t1) at (5.8,0.3){{\small{抽取得到的规则(子树对齐)}}}; \node[anchor=north](t1) at (4.7,0.3){{\footnotesize{抽取得到的规则(子树对齐)}}};
\node[anchor=north](t2) at ([xshift=2.9em,yshift=0.5em]t1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}}; \node[anchor=north](t2) at ([xshift=3.7em,yshift=0.5em]t1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}};
\node[anchor=north](t3) at ([xshift=-7.7em,yshift=0.0em]t2.south){\color{gray!70}\small{$r_1$}}; \node[anchor=north](t3) at ([xshift=-7.7em,yshift=0.0em]t2.south){\color{gray!70}\footnotesize{$r_1$}};
\node[anchor=west](t3-1) at ([xshift=0.0em,yshift=0.0em]t3.east){\color{gray!70}\small{AS(了) $\rightarrow$ DT(the)}}; \node[anchor=west](t3-1) at ([xshift=0.0em,yshift=0.0em]t3.east){\color{gray!70}\footnotesize{AS(了) $\rightarrow$ DT(the)}};
\node[anchor=north](t4) at ([xshift=0.0em,yshift=0.0em]t3.south){\color{gray!70}\small{$r_2$}}; \node[anchor=north](t4) at ([xshift=0.0em,yshift=0.0em]t3.south){\color{gray!70}\footnotesize{$r_2$}};
\node[anchor=west](t4-1) at ([xshift=0.0em,yshift=0.0em]t4.east){\color{gray!70}\small{NN(进口) $\rightarrow$ NNS(imports)}}; \node[anchor=west](t4-1) at ([xshift=0.0em,yshift=0.0em]t4.east){\color{gray!70}\footnotesize{NN(进口) $\rightarrow$ NNS(imports)}};
\node[anchor=north](t5) at ([xshift=0.0em,yshift=0.0em]t4.south){\small{$r_3$}}; \node[anchor=north](t5) at ([xshift=0.0em,yshift=0.0em]t4.south){\footnotesize{$r_3$}};
\node[anchor=west](t5-1) at ([xshift=0.0em,yshift=0.0em]t5.east){\small{AD(大幅度) $\rightarrow$ RB(drastically)}}; \node[anchor=west](t5-1) at ([xshift=0.0em,yshift=0.0em]t5.east){\footnotesize{AD(大幅度) $\rightarrow$ RB(drastically)}};
\node[anchor=north](t6) at ([xshift=0.0em,yshift=0.0em]t5.south){\small{$r_4$}}; \node[anchor=north](t6) at ([xshift=0.0em,yshift=0.0em]t5.south){\footnotesize{$r_4$}};
\node[anchor=west](t6-1) at ([xshift=0.0em,yshift=0.0em]t6.east){\small{VV(下降) $\rightarrow$ VBN(fallen)}}; \node[anchor=west](t6-1) at ([xshift=0.0em,yshift=0.0em]t6.east){\footnotesize{VV(下降) $\rightarrow$ VBN(fallen)}};
\node[anchor=north](t7) at ([xshift=0.0em,yshift=0.0em]t6.south){\color{gray!70}\small{$r_5$}}; \node[anchor=north](t7) at ([xshift=0.0em,yshift=0.0em]t6.south){\color{gray!70}\footnotesize{$r_5$}};
\node[anchor=west](t7-1) at ([xshift=0.0em,yshift=0.0em]t7.east){\color{gray!70}\small{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$}}; \node[anchor=west](t7-1) at ([xshift=0.0em,yshift=0.0em]t7.east){\color{gray!70}\footnotesize{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$}};
\node[anchor=north](t8) at ([xshift=9.4em,yshift=0.0em]t7.south){\color{gray!70}\scriptsize{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}}; \node[anchor=north](t8) at ([xshift=9.4em,yshift=0.0em]t7.south){\color{gray!70}\scriptsize{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}};
\node[anchor=north](s3) at ([xshift=0.0em,yshift=-1.3em]t7.south){\red{\small{$r_{6}$}}}; \node[anchor=north](s3) at ([xshift=0.0em,yshift=-1.3em]t7.south){\red{\footnotesize{$r_{6}$}}};
\node[anchor=west](s3-1) at ([xshift=0.0em,yshift=0.0em]s3.east){\red{\small{AS(了) $\rightarrow$ VBZ(have)}}}; \node[anchor=west](s3-1) at ([xshift=0.0em,yshift=0.0em]s3.east){\red{\footnotesize{AS(了) $\rightarrow$ VBZ(have)}}};
\node[anchor=north](s4) at ([xshift=0.0em,yshift=0.0em]s3.south){\red{\small{$r_{7}$}}}; \node[anchor=north](s4) at ([xshift=0.0em,yshift=0.0em]s3.south){\red{\footnotesize{$r_{7}$}}};
\node[anchor=west](s4-1) at ([xshift=0.0em,yshift=0.0em]s4.east){\red{\small{NN(进口) $\rightarrow$}}}; \node[anchor=west](s4-1) at ([xshift=0.0em,yshift=0.0em]s4.east){\red{\footnotesize{NN(进口) $\rightarrow$}}};
\node[anchor=north](s5) at ([xshift=0.0em,yshift=0.0em]s4.south){\small{\color{white}{$r_{?}$}}}; \node[anchor=north](s5) at ([xshift=0.0em,yshift=0.0em]s4.south){\footnotesize{\color{white}{$r_{?}$}}};
\node[anchor=west](s5-1) at ([xshift=0.0em,yshift=0.0em]s5.east){\red{\small{NP(DT(the) NNS(imports))}}}; \node[anchor=west](s5-1) at ([xshift=0.0em,yshift=0.0em]s5.east){\red{\footnotesize{NP(DT(the) NNS(imports))}}};
\node[anchor=north](s6) at ([xshift=0.0em,yshift=0.0em]s5.south){\red{\small{$r_{8}$}}}; \node[anchor=north](s6) at ([xshift=0.0em,yshift=0.0em]s5.south){\red{\footnotesize{$r_{8}$}}};
\node[anchor=west](s6-1) at ([xshift=0.0em,yshift=0.0em]s6.east){\red{\small{VP(AD$_1$ VP(VV$_2$ AS$_3$)) $\rightarrow$}}}; \node[anchor=west](s6-1) at ([xshift=0.0em,yshift=0.0em]s6.east){\red{\footnotesize{VP(AD$_1$ VP(VV$_2$ AS$_3$)) $\rightarrow$}}};
\node[anchor=north](s7) at ([xshift=0.0em,yshift=0.0em]s6.south){\red{\small{\color{white}{$r_{?}$}}}}; \node[anchor=north](s7) at ([xshift=0.0em,yshift=0.0em]s6.south){\red{\footnotesize{\color{white}{$r_{?}$}}}};
\node[anchor=west](s7-1) at ([xshift=0.0em,yshift=0.0em]s7.east){\red{\small{VP(VBZ$_3$ ADVP(RB$_1$ VBN$_2$)}}}; \node[anchor=west](s7-1) at ([xshift=0.0em,yshift=0.0em]s7.east){\red{\footnotesize{VP(VBZ$_3$ ADVP(RB$_1$ VBN$_2$)}}};
\node[anchor=north](s8) at ([xshift=0.0em,yshift=0.0em]s7.south){\red{\small{$r_{9}$}}}; \node[anchor=north](s8) at ([xshift=0.0em,yshift=0.0em]s7.south){\red{\footnotesize{$r_{9}$}}};
\node[anchor=west](s8-1) at ([xshift=0.0em,yshift=0.0em]s8.east){\red{\small{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)}}}; \node[anchor=west](s8-1) at ([xshift=0.0em,yshift=0.0em]s8.east){\red{\footnotesize{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)}}};
\end{tikzpicture} \end{tikzpicture}
Book/Chapter4/Figures/tree-to-tree-rule-extraction-base-word-alignment.tex
...@@ -44,28 +44,30 @@ ...@@ -44,28 +44,30 @@
\end{scope} \end{scope}
\node[anchor=north](t1) at (4.5,0.3){{\small{抽取得到的规则}}}; \node[anchor=north](t1) at (4.5,0.3){{\footnotesize{抽取得到的规则}}};
\node[anchor=north](t2) at ([xshift=5.5em,yshift=0.5em]t1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}}; \node[anchor=north](t2) at ([xshift=5.5em,yshift=0.5em]t1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}};
\node[anchor=north](t3) at ([xshift=-7.7em,yshift=0.0em]t2.south){\small{$r_1$}}; \node[anchor=north](t3) at ([xshift=-7.7em,yshift=0.0em]t2.south){\footnotesize{$r_1$}};
\node[anchor=west](t3-1) at ([xshift=0.0em,yshift=0.0em]t3.east){\small{AS(了) $\rightarrow$ DT(the)}}; \node[anchor=west](t3-1) at ([xshift=0.0em,yshift=0.0em]t3.east){\footnotesize{AS(了) $\rightarrow$ DT(the)}};
\node[anchor=north](t4) at ([xshift=0.0em,yshift=0.0em]t3.south){\small{$r_2$}}; \node[anchor=north](t4) at ([xshift=0.0em,yshift=0.0em]t3.south){\footnotesize{$r_2$}};
\node[anchor=west](t4-1) at ([xshift=0.0em,yshift=0.0em]t4.east){\small{NN(进口) $\rightarrow$ NNS(imports)}}; \node[anchor=west](t4-1) at ([xshift=0.0em,yshift=0.0em]t4.east){\footnotesize{NN(进口) $\rightarrow$ NNS(imports)}};
\node[anchor=north](t5) at ([xshift=0.0em,yshift=0.0em]t4.south){\small{$r_3$}}; \node[anchor=north](t5) at ([xshift=0.0em,yshift=0.0em]t4.south){\footnotesize{$r_3$}};
\node[anchor=west](t5-1) at ([xshift=0.0em,yshift=0.0em]t5.east){\small{AD(大幅度) $\rightarrow$ RB(drastically)}}; \node[anchor=west](t5-1) at ([xshift=0.0em,yshift=0.0em]t5.east){\footnotesize{AD(大幅度) $\rightarrow$ RB(drastically)}};
\node[anchor=north](t6) at ([xshift=0.0em,yshift=0.0em]t5.south){\small{$r_4$}}; \node[anchor=north](t6) at ([xshift=0.0em,yshift=0.0em]t5.south){\footnotesize{$r_4$}};
\node[anchor=west](t6-1) at ([xshift=0.0em,yshift=0.0em]t6.east){\small{VV(下降) $\rightarrow$ VBN(fallen)}}; \node[anchor=west](t6-1) at ([xshift=0.0em,yshift=0.0em]t6.east){\footnotesize{VV(下降) $\rightarrow$ VBN(fallen)}};
\node[anchor=north](t7) at ([xshift=0.0em,yshift=0.0em]t6.south){\small{$r_6$}}; \node[anchor=north](t7) at ([xshift=0.0em,yshift=0.0em]t6.south){\footnotesize{$r_6$}};
\node[anchor=west](t7-1) at ([xshift=0.0em,yshift=0.0em]t7.east){\small{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$}}; \node[anchor=west](t7-1) at ([xshift=0.0em,yshift=0.0em]t7.east){\footnotesize{IP(NN$_1$ VP(AD$_2$ VP(VV$_3$ AS$_4$)) $\rightarrow$}};
\node[anchor=north](t8) at ([xshift=9.4em,yshift=0.0em]t7.south){\scriptsize{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}}; \node[anchor=north](t8) at ([xshift=9.4em,yshift=0.0em]t7.south){\scriptsize{S(NP(DT$_4$ NNS$_1$) VP(VBZ(have) ADVP(RB$_2$ VBN$_3$))}};
\node[anchor=north](s1) at ([yshift=-8.0em]t1.south){{\small{无法得到的规则}}}; \node[anchor=north](s1) at ([yshift=-8.0em]t1.south){{\footnotesize{无法得到的规则}}};
\node[anchor=north](s2) at ([xshift=5.5em,yshift=0.5em]s1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}}; \node[anchor=north](s2) at ([xshift=5.5em,yshift=0.5em]s1.south){\underline{\qquad \qquad \qquad \quad \qquad \qquad \qquad \qquad \qquad}};
\node[anchor=north](s3) at ([xshift=-7.7em,yshift=0.0em]s2.south){\small{$r_{?}$}}; \node[anchor=north](s3) at ([xshift=-7.7em,yshift=0.0em]s2.south){\footnotesize{$r_{?}$}};
\node[anchor=west](s3-1) at ([xshift=0.0em,yshift=0.0em]s3.east){\small{AS(了) $\rightarrow$ VBZ(have)}}; \node[anchor=west](s3-1) at ([xshift=0.0em,yshift=0.0em]s3.east){\footnotesize{AS(了) $\rightarrow$ VBZ(have)}};
\node[anchor=north](s4) at ([xshift=0.0em,yshift=0.0em]s3.south){\small{$r_{?}$}}; \node[anchor=north](s4) at ([xshift=0.0em,yshift=0.0em]s3.south){\footnotesize{$r_{?}$}};
\node[anchor=west](s4-1) at ([xshift=0.0em,yshift=0.0em]s4.east){\small{NN(进口) $\rightarrow$}\small{NP(DT(the) NNS(imports))}}; \node[anchor=west](s4-1) at ([xshift=0.0em,yshift=0.0em]s4.east){\footnotesize{NN(进口) $\rightarrow$}};
\node[anchor=north](s6) at ([xshift=0.0em,yshift=0.0em]s4.south){\small{$r_{?}$}}; \node[anchor=north](s5) at ([xshift=0.0em,yshift=0.0em]s4.south){\footnotesize{\color{white}{$r_{?}$}}};
\node[anchor=west](s6-1) at ([xshift=0.0em,yshift=0.0em]s6.east){\small{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)}}; \node[anchor=west](s5-1) at ([xshift=0.0em,yshift=0.0em]s5.east){\footnotesize{NP(DT(the) NNS(imports))}};
\node[anchor=north](s6) at ([xshift=0.0em,yshift=0.0em]s5.south){\footnotesize{$r_{?}$}};
\node[anchor=west](s6-1) at ([xshift=0.0em,yshift=0.0em]s6.east){\footnotesize{IP(NN$_1$ VP$_2$) $\rightarrow$ S(NP$_1$ VP$_2$)}};
\end{tikzpicture} \end{tikzpicture}
......
Book/Chapter4/chapter4.tex
...@@ -18,7 +18,7 @@ ...@@ -18,7 +18,7 @@
\section{翻译中的结构信息}\index{Chapter4.1} \section{翻译中的结构信息}\index{Chapter4.1}
\parinterval 首先，回顾一下基于单词的统计翻译模型是如何完成翻译的。图\ref{fig:example-of-translation-base-word}展示了一个实例。其中，左侧是一个单词的``翻译表''，它记录了源语言（中文）单词和目标语言（英文）单词之间的对应关系，以及这种对应的可能性大小（用P表示）。在翻译时，会使用这些单词一级的对应，生成目标语译文。比如，图\ref{fig:example-of-translation-base-word}右侧就展示了一个基于词的模型生成的翻译结果，其中\textbf{s}和\textbf{t}分别表示源语言和目标语言句子，单词之间的连线表示两个句子中单词一级的对应。 \parinterval 首先，回顾一下基于单词的统计翻译模型是如何完成翻译的。图\ref{fig:example-of-translation-base-word}展示了一个实例。其中，左侧是一个单词的``翻译表''，它记录了源语言（中文）单词和目标语言（英文）单词之间的对应关系，以及这种对应的可能性大小（用P表示）。在翻译时，会使用这些单词一级的对应，生成目标语译文。比如，图\ref{fig:example-of-translation-base-word}右侧就展示了一个基于词的模型生成的翻译结果，其中\textbf{s}和\textbf{t}分别表示源语言和目标语言句子，单词之间的连线表示两个句子中单词一级的对应。
\parinterval sadadas
%---------------------------------------------- %----------------------------------------------
% 图4.1 % 图4.1
\begin{figure}[htp] \begin{figure}[htp]
...@@ -1767,8 +1767,8 @@ r_9: \quad \textrm{IP(}\textrm{NN}_1\ \textrm{VP}_2) \rightarrow \textrm{S(}\tex ...@@ -1767,8 +1767,8 @@ r_9: \quad \textrm{IP(}\textrm{NN}_1\ \textrm{VP}_2) \rightarrow \textrm{S(}\tex
% 图 % 图
\begin{figure}[htp] \begin{figure}[htp]
\centering \centering
\begin{tabular}{l l l} \begin{tabular}{l l}
& \subfigure{\input{./Chapter4/Figures/combine-minimum-rule-1}} & \subfigure{\input{./Chapter4/Figures/combine-minimum-rule-2}} \subfigure{\input{./Chapter4/Figures/combine-minimum-rule-1}} & \subfigure{\input{./Chapter4/Figures/combine-minimum-rule-2}}
\end{tabular} \end{tabular}
\caption{对最小规则进行组合（绿色矩形）} \caption{对最小规则进行组合（绿色矩形）}
\label{fig:combine-minimum-rule} \label{fig:combine-minimum-rule}
......
Book/bibliography.bib
This source diff could not be displayed because it is too large. You can view the blob instead.
Book/mt-book-xelatex.bbl
This source diff could not be displayed because it is too large. You can view the blob instead.
Book/structure.tex
...@@ -74,7 +74,7 @@ ...@@ -74,7 +74,7 @@
% BIBLIOGRAPHY AND INDEX % BIBLIOGRAPHY AND INDEX
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\usepackage[style=numeric,citestyle=numeric,sorting=nyt,sortcites=true,maxbibnames=4,minbibnames=3,autopunct=true,babel=hyphen,hyperref=true,abbreviate=false,backref=true,backend=biber]{biblatex} \usepackage[style=numeric,citestyle=numeric,sorting=nyt,sortcites=true,maxbibnames=40,minbibnames=30,autopunct=true,babel=hyphen,hyperref=true,abbreviate=false,backref=true,backend=biber]{biblatex}
%maxbibnames 设置参考文献最多显示作者数目 %maxbibnames 设置参考文献最多显示作者数目
%minbibnames 如果作者数目超过maxbibnames，则只显示minbibnames个作者 %minbibnames 如果作者数目超过maxbibnames，则只显示minbibnames个作者
\addbibresource{bibliography.bib} % BibTeX bibliography file \addbibresource{bibliography.bib} % BibTeX bibliography file
......
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