figure

Book/Chapter1/chapter1.tex

@@ -45,7 +45,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter1/Figures/figure-Required-parts-of-MT}
+\input{./Chapter1/Figures/figure-required-parts-of-mt}
     \caption{机器翻译系统的组成}
     \caption{机器翻译系统的组成}
     \label{fig:1-2}
     \label{fig:1-2}
 \end{figure}
 \end{figure}
@@ -220,7 +220,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter1/Figures/figure-Example-RBMT}
+\input{./Chapter1/Figures/figure-example-rbmt}
 \setlength{\belowcaptionskip}{-1.5em}
 \setlength{\belowcaptionskip}{-1.5em}
     \caption{基于规则的机器翻译的示例图（左：规则库；右：规则匹配结果）}
     \caption{基于规则的机器翻译的示例图（左：规则库；右：规则匹配结果）}
     \label{fig:1-8}
     \label{fig:1-8}
@@ -290,7 +290,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter1/Figures/figure-Example-SMT}
+\input{./Chapter1/Figures/figure-example-smt}
     \caption{统计机器翻译的示例图（左：语料资源；中：翻译模型与语言模型；右：翻译假设与翻译引擎）}
     \caption{统计机器翻译的示例图（左：语料资源；中：翻译模型与语言模型；右：翻译假设与翻译引擎）}
     \label{fig:1-11}
     \label{fig:1-11}
 \end{figure}
 \end{figure}
@@ -311,7 +311,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter1/Figures/figure-Example-NMT}
+\input{./Chapter1/Figures/figure-example-nmt}
     \caption{神经机器翻译的示例图（左：编码器-解码器网络；右：编码器示例网络）}
     \caption{神经机器翻译的示例图（左：编码器-解码器网络；右：编码器示例网络）}
     \label{fig:1-12}
     \label{fig:1-12}
 \end{figure}
 \end{figure}

Book/Chapter2/chapter2.tex

@@ -35,8 +35,8 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
- 	\subfigure[机器翻译系统被看作一个黑盒] {\input{./Chapter2/Figures/figure-MT-system-as-a-black-box}  }
- 	\subfigure[机器翻系统 = 前/后处理 + 翻译引擎] {\input{./Chapter2/Figures/figure-MT=language-analysis+translation-engine}}
+ 	\subfigure[机器翻译系统被看作一个黑盒] {\input{./Chapter2/Figures/figure-mt-system-as-a-black-box}  }
+ 	\subfigure[机器翻系统 = 前/后处理 + 翻译引擎] {\input{./Chapter2/Figures/figure-mt=language-analysis+translation-engine}}
 	\caption{机器翻译系统的结构}
 	\caption{机器翻译系统的结构}
     \label{fig:2-1}
     \label{fig:2-1}
 \end{figure}
 \end{figure}
@@ -125,7 +125,7 @@ F(X)=\int_{-\infty}^x f(x)dx
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
- \input{./Chapter2/Figures/figure-Probability-density-function&Distribution-function}
+ \input{./Chapter2/Figures/figure-probability-density-function&distribution-function}
 \caption{一个概率密度函数(左)与其对应的分布函数(右)}
 \caption{一个概率密度函数(左)与其对应的分布函数(右)}
 \label{fig:2-3}
 \label{fig:2-3}
 \end{figure}
 \end{figure}
@@ -310,7 +310,7 @@ F(X)=\int_{-\infty}^x f(x)dx
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter2/Figures/figure-Self-information-function}
+\input{./Chapter2/Figures/figure-self-information-function}
 \caption{自信息函数$\textrm{I}(x)$关于$\textrm{P}(x)$的曲线}
 \caption{自信息函数$\textrm{I}(x)$关于$\textrm{P}(x)$的曲线}
 \label{fig:2-6}
 \label{fig:2-6}
 \end{figure}
 \end{figure}
@@ -429,7 +429,7 @@ F(X)=\int_{-\infty}^x f(x)dx
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter2/Figures/figure-Example-of-word-segmentation-based-on-dictionary}
+\input{./Chapter2/Figures/figure-example-of-word-segmentation-based-on-dictionary}
 \caption{基于词典进行分词的实例}
 \caption{基于词典进行分词的实例}
 \label{fig:2-8}
 \label{fig:2-8}
 \end{figure}
 \end{figure}
@@ -638,7 +638,7 @@ F(X)=\int_{-\infty}^x f(x)dx
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter2/Figures/figure-examples-of-Chinese-word-segmentation-based-on-1-gram-model}
+\input{./Chapter2/Figures/figure-examples-of-chinese-word-segmentation-based-on-1-gram-model}
 \caption{基于1-gram语言模型的中文分词实例}
 \caption{基于1-gram语言模型的中文分词实例}
 \label{fig:2-17}
 \label{fig:2-17}
 \end{figure}
 \end{figure}

Book/Chapter3/Chapter3.tex

@@ -170,7 +170,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter3/Figures/figure-processes-SMT}
+\input{./Chapter3/Figures/figure-processes-smt}
     \caption{简单的统计机器翻译流程}
     \caption{简单的统计机器翻译流程}
     \label{fig:3-5}
     \label{fig:3-5}
 \end{figure}
 \end{figure}
@@ -472,7 +472,7 @@ g(\mathbf{s},\mathbf{t}) \equiv \prod_{j,i \in \widehat{A}}{\textrm{P}(s_j,t_i)}
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\input{./Chapter3/Figures/figure-greedy-MT-decoding-pseudo-code}
+\input{./Chapter3/Figures/figure-greedy-mt-decoding-pseudo-code}
     \caption{贪婪的机器翻译解码算法的伪代码}
     \caption{贪婪的机器翻译解码算法的伪代码}
     \label{fig:3-10}
     \label{fig:3-10}
 \end{figure}
 \end{figure}
@@ -483,8 +483,8 @@ g(\mathbf{s},\mathbf{t}) \equiv \prod_{j,i \in \widehat{A}}{\textrm{P}(s_j,t_i)}
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-\subfigure{\input{./Chapter3/Figures/greedy-MT-decoding-process-1}}
-\subfigure{\input{./Chapter3/Figures/greedy-MT-decoding-process-3}}
+\subfigure{\input{./Chapter3/Figures/greedy-mt-decoding-process-1}}
+\subfigure{\input{./Chapter3/Figures/greedy-mt-decoding-process-3}}
 \setlength{\belowcaptionskip}{14.0em}
 \setlength{\belowcaptionskip}{14.0em}
     \caption{贪婪的机器翻译解码过程实例}
     \caption{贪婪的机器翻译解码过程实例}
     \label{fig:3-11}
     \label{fig:3-11}

Book/Chapter4/chapter4.tex

@@ -2162,7 +2162,7 @@ d_1 = {d'} \circ {r_5}
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter4/Figures/structure-of-Chart}
+\input{./Chapter4/Figures/structure-of-chart}
 \caption{Chart结构}
 \caption{Chart结构}
 \label{fig:4-65}
 \label{fig:4-65}
 \end{figure}
 \end{figure}
@@ -2252,7 +2252,7 @@ d_1 = {d'} \circ {r_5}
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter4/Figures/content-of-Chart-in-tree-based-decoding}
+\input{./Chapter4/Figures/content-of-chart-in-tree-based-decoding}
 \caption{基于树的解码中Chart的内容}
 \caption{基于树的解码中Chart的内容}
 \label{fig:4-68}
 \label{fig:4-68}
 \end{figure}
 \end{figure}

Book/Chapter6/Chapter6.tex

@@ -252,7 +252,7 @@ NMT                     & $ 21.7^{\ast}$          & $18.7^{\ast}$           & -1
 % 图3.6
 % 图3.6
 \begin{figure}[htp]
 \begin{figure}[htp]
     \centering
     \centering
-    \input{./Chapter6/Figures/figure-Presentation-space}
+    \input{./Chapter6/Figures/figure-presentation-space}
     \caption{统计机器翻译和神经机器翻译的表示空间}
     \caption{统计机器翻译和神经机器翻译的表示空间}
     \label{fig:6-6}
     \label{fig:6-6}
 \end{figure}
 \end{figure}
@@ -288,7 +288,7 @@ NMT                     & $ 21.7^{\ast}$          & $18.7^{\ast}$           & -1
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-A-working-example-of-neural-machine-translation}
+\input{./Chapter6/Figures/figure-a-working-example-of-neural-machine-translation}
 \caption{神经机器翻译的运行实例}
 \caption{神经机器翻译的运行实例}
 \label{fig:6-7}
 \label{fig:6-7}
 \end{figure}
 \end{figure}
@@ -384,7 +384,7 @@ NMT                     & $ 21.7^{\ast}$          & $18.7^{\ast}$           & -1
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Structure-of-a-recurrent-network-model}
+\input{./Chapter6/Figures/figure-structure-of-a-recurrent-network-model}
 \caption{循环网络模型的结构}
 \caption{循环网络模型的结构}
 \label{fig:6-9}
 \label{fig:6-9}
 \end{figure}
 \end{figure}
@@ -396,7 +396,7 @@ NMT                     & $ 21.7^{\ast}$          & $18.7^{\ast}$           & -1
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Model-structure-based-on-recurrent-neural-network-translation}
+\input{./Chapter6/Figures/figure-model-structure-based-on-recurrent-neural-network-translation}
 \caption{基于循环神经网络翻译的模型结构}
 \caption{基于循环神经网络翻译的模型结构}
 \label{fig:6-10}
 \label{fig:6-10}
 \end{figure}
 \end{figure}
@@ -480,7 +480,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Word-embedding-structure}
+\input{./Chapter6/Figures/figure-word-embedding-structure}
 \caption{词嵌入层结构}
 \caption{词嵌入层结构}
 \label{fig:6-12}
 \label{fig:6-12}
 \end{figure}
 \end{figure}
@@ -494,7 +494,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Output-layer-structur}
+\input{./Chapter6/Figures/figure-output-layer-structur}
 \caption{输出层结构}
 \caption{输出层结构}
 \label{fig:6-13}
 \label{fig:6-13}
 \end{figure}
 \end{figure}
@@ -525,7 +525,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
 % \includegraphics[scale=0.7]{./Chapter6/Figures/Softmax.png}
 % \includegraphics[scale=0.7]{./Chapter6/Figures/Softmax.png}
-\input{./Chapter6/Figures/figure-Softmax}
+\input{./Chapter6/Figures/figure-softmax}
 \caption{ Softmax函数（一维）所对应的曲线}
 \caption{ Softmax函数（一维）所对应的曲线}
 \label{fig:6-14}
 \label{fig:6-14}
 \end{figure}
 \end{figure}
@@ -697,7 +697,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Double-layer-RNN} \hspace{10em}
+\input{./Chapter6/Figures/figure-double-layer-RNN} \hspace{10em}
 \caption{双层循环神经网络}
 \caption{双层循环神经网络}
 \label{fig:6-19}
 \label{fig:6-19}
 \end{figure}
 \end{figure}
@@ -744,7 +744,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Attention-of-source-and-target-words}
+\input{./Chapter6/Figures/figure-attention-of-source-and-target-words}
 \caption{源语词和目标语词的关注度}
 \caption{源语词和目标语词的关注度}
 \label{fig:6-21}
 \label{fig:6-21}
 \end{figure}
 \end{figure}
@@ -758,7 +758,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-encoder-decoder-with-Attention}
+\input{./Chapter6/Figures/figure-encoder-decoder-with-attention}
 \caption{不使用(a)和使用(b)注意力机制的翻译模型对比}
 \caption{不使用(a)和使用(b)注意力机制的翻译模型对比}
 \label{fig:6-22}
 \label{fig:6-22}
 \end{figure}
 \end{figure}
@@ -780,7 +780,7 @@ $\textrm{P}({y_j | \mathbf{s}_{j-1} ,y_{j-1},\mathbf{C}})$由Softmax实现，Sof
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Calculation-process-of-context-vector-C}
+\input{./Chapter6/Figures/figure-calculation-process-of-context-vector-C}
 \caption{上下文向量$\mathbf{C}_j$的计算过程}
 \caption{上下文向量$\mathbf{C}_j$的计算过程}
 \label{fig:6-23}
 \label{fig:6-23}
 \end{figure}
 \end{figure}
@@ -824,7 +824,7 @@ a (\mathbf{s},\mathbf{h}) =  \left\{ \begin{array}{ll}
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Matrix-Representation-of-Attention-Weights-Between-Chinese-English-Sentence-Pairs}
+\input{./Chapter6/Figures/figure-matrix-representation-of-attention-weights-between-chinese-english-sentence-pairs}
 \caption{一个汉英句对之间的注意力权重{$\alpha_{i,j}$}的矩阵表示}
 \caption{一个汉英句对之间的注意力权重{$\alpha_{i,j}$}的矩阵表示}
 \label{fig:6-24}
 \label{fig:6-24}
 \end{figure}
 \end{figure}
@@ -837,7 +837,7 @@ a (\mathbf{s},\mathbf{h}) =  \left\{ \begin{array}{ll}
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Example-of-context-vector-calculation-process}
+\input{./Chapter6/Figures/figure-example-of-context-vector-calculation-process}
 \caption{上下文向量计算过程实例}
 \caption{上下文向量计算过程实例}
 \label{fig:6-25}
 \label{fig:6-25}
 \end{figure}
 \end{figure}
@@ -878,7 +878,7 @@ a (\mathbf{s},\mathbf{h}) =  \left\{ \begin{array}{ll}
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Query-model-corresponding-to-traditional-query-model-vs-attention-mechanism}
+\input{./Chapter6/Figures/figure-query-model-corresponding-to-traditional-query-model-vs-attention-mechanism}
 \caption{传统查询模型(a)和注意力机制所对应的查询模型(b)}
 \caption{传统查询模型(a)和注意力机制所对应的查询模型(b)}
 \label{fig:6-26}
 \label{fig:6-26}
 \end{figure}
 \end{figure}
@@ -898,7 +898,7 @@ a (\mathbf{s},\mathbf{h}) =  \left\{ \begin{array}{ll}
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Query-model-corresponding-to-attention-mechanism}
+\input{./Chapter6/Figures/figure-query-model-corresponding-to-attention-mechanism}
 \caption{注意力机制所对应的查询模型}
 \caption{注意力机制所对应的查询模型}
 \label{fig:6-27}
 \label{fig:6-27}
 \end{figure}
 \end{figure}
@@ -1012,7 +1012,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Relationship-between-learning-rate-and-number-of-updates}
+\input{./Chapter6/Figures/figure-relationship-between-learning-rate-and-number-of-updates}
 \caption{学习率与更新次数的变化关系}
 \caption{学习率与更新次数的变化关系}
 \label{fig:6-29}
 \label{fig:6-29}
 \end{figure}
 \end{figure}
@@ -1054,7 +1054,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Data-parallel-process}
+\input{./Chapter6/Figures/figure-data-parallel-process}
 \caption{数据并行过程}
 \caption{数据并行过程}
 \label{fig:6-30}
 \label{fig:6-30}
 \end{figure}
 \end{figure}
@@ -1112,7 +1112,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Decoding-process-based-on-greedy-method}
+\input{./Chapter6/Figures/figure-decoding-process-based-on-greedy-method}
 \caption{基于贪婪方法的解码过程}
 \caption{基于贪婪方法的解码过程}
 \label{fig:6-32}
 \label{fig:6-32}
 \end{figure}
 \end{figure}
@@ -1124,7 +1124,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Decode-the-word-probability-distribution-at-the-first-position}
+\input{./Chapter6/Figures/figure-decode-the-word-probability-distribution-at-the-first-position}
 \caption{解码第一个位置输出的单词概率分布（``Have''的概率最高）}
 \caption{解码第一个位置输出的单词概率分布（``Have''的概率最高）}
 \label{fig:6-33}
 \label{fig:6-33}
 \end{figure}
 \end{figure}
@@ -1147,7 +1147,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Beam-search-process}
+\input{./Chapter6/Figures/figure-beam-search-process}
 \caption{束搜索过程}
 \caption{束搜索过程}
 \label{fig:6-34}
 \label{fig:6-34}
 \end{figure}
 \end{figure}
@@ -1285,7 +1285,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Dependencies-between-words-in-a-recurrent-neural-network}
+\input{./Chapter6/Figures/figure-dependencies-between-words-in-a-recurrent-neural-network}
 \caption{循环神经网络中单词之间的依赖关系}
 \caption{循环神经网络中单词之间的依赖关系}
 \label{fig:6-36}
 \label{fig:6-36}
 \end{figure}
 \end{figure}
@@ -1297,7 +1297,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Dependencies-between-words-of-Attention}
+\input{./Chapter6/Figures/figure-dependencies-between-words-of-attention}
 \caption{自注意力机制中单词之间的依赖关系}
 \caption{自注意力机制中单词之间的依赖关系}
 \label{fig:6-37}
 \label{fig:6-37}
 \end{figure}
 \end{figure}
@@ -1309,7 +1309,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Example-of-self-attention-mechanism-calculation}
+\input{./Chapter6/Figures/figure-example-of-self-attention-mechanism-calculation}
 \caption{自注意力计算实例}
 \caption{自注意力计算实例}
 \label{fig:6-38}
 \label{fig:6-38}
 \end{figure}
 \end{figure}
@@ -1383,7 +1383,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Calculation-of-context-vector-C}
+\input{./Chapter6/Figures/figure-calculation-of-context-vector-C}
 \caption{上下文向量$\mathbf{C}$的计算}
 \caption{上下文向量$\mathbf{C}$的计算}
 \label{fig:6-41}
 \label{fig:6-41}
 \end{figure}
 \end{figure}
@@ -1418,7 +1418,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-A-combination-of-position-encoding-and-word-encoding}
+\input{./Chapter6/Figures/figure-a-combination-of-position-encoding-and-word-encoding}
 \caption{位置编码与词编码的组合}
 \caption{位置编码与词编码的组合}
 \label{fig:6-43}
 \label{fig:6-43}
 \end{figure}
 \end{figure}
@@ -1448,7 +1448,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Position-of-self-attention-mechanism-in-the-model}
+\input{./Chapter6/Figures/figure-position-of-self-attention-mechanism-in-the-model}
 \caption{自注意力机制在模型中的位置}
 \caption{自注意力机制在模型中的位置}
 \label{fig:6-44}
 \label{fig:6-44}
 \end{figure}
 \end{figure}
@@ -1479,7 +1479,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Point-product-attention-model}
+\input{./Chapter6/Figures/figure-point-product-attention-model}
 \caption{点乘注意力力模型 }
 \caption{点乘注意力力模型 }
 \label{fig:6-45}
 \label{fig:6-45}
 \end{figure}
 \end{figure}
@@ -1511,7 +1511,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Mask-instance-for-future-positions-in-Transformer}
+\input{./Chapter6/Figures/figure-mask-instance-for-future-positions-in-transformer}
 \caption{Transformer中对于未来位置进行的屏蔽的Mask实例}
 \caption{Transformer中对于未来位置进行的屏蔽的Mask实例}
 \label{fig:6-47}
 \label{fig:6-47}
 \end{figure}
 \end{figure}
@@ -1535,7 +1535,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Multi-Head-Attention-Model}
+\input{./Chapter6/Figures/figure-multi-head-attention-model}
 \caption{多头注意力模型}
 \caption{多头注意力模型}
 \label{fig:6-48}
 \label{fig:6-48}
 \end{figure}
 \end{figure}
@@ -1560,7 +1560,7 @@ L(\mathbf{Y},\widehat{\mathbf{Y}}) = \sum_{j=1}^n L_{\textrm{ce}}(\mathbf{y}_j,\
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Residual-network-structure}
+\input{./Chapter6/Figures/figure-residual-network-structure}
 \caption{残差网络结构}
 \caption{残差网络结构}
 \label{fig:6-49}
 \label{fig:6-49}
 \end{figure}
 \end{figure}
@@ -1579,7 +1579,7 @@ x_{l+1} = x_l + \digamma (x_l)
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Position-of-difference-and-layer-regularization-in-the-model}
+\input{./Chapter6/Figures/figure-position-of-difference-and-layer-regularization-in-the-model}
 \caption{残差和层正则化在模型中的位置}
 \caption{残差和层正则化在模型中的位置}
 \label{fig:6-50}
 \label{fig:6-50}
 \end{figure}
 \end{figure}
@@ -1600,7 +1600,7 @@ x_{l+1} = x_l + \digamma (x_l)
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Different-regularization-methods}
+\input{./Chapter6/Figures/figure-different-regularization-methods}
 \caption{不同正则化方式 }
 \caption{不同正则化方式 }
 \label{fig:6-51}
 \label{fig:6-51}
 \end{figure}
 \end{figure}
@@ -1613,7 +1613,7 @@ x_{l+1} = x_l + \digamma (x_l)
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Position-of-feedforward-neural-network-in-the-model}
+\input{./Chapter6/Figures/figure-position-of-feedforward-neural-network-in-the-model}
 \caption{前馈神经网络在模型中的位置}
 \caption{前馈神经网络在模型中的位置}
 \label{fig:6-52}
 \label{fig:6-52}
 \end{figure}
 \end{figure}
@@ -1636,7 +1636,7 @@ x_{l+1} = x_l + \digamma (x_l)
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Structure-of-the-network-during-Transformer-training}
+\input{./Chapter6/Figures/figure-structure-of-the-network-during-transformer-training}
 \caption{Transformer训练时网络的结构}
 \caption{Transformer训练时网络的结构}
 \label{fig:6-53}
 \label{fig:6-53}
 \end{figure}
 \end{figure}
@@ -1676,7 +1676,7 @@ lrate = d_{model}^{-0.5} \cdot \textrm{min} (step^{-0.5} , step \cdot warmup\_st
 % 图3.10
 % 图3.10
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Comparison-of-the-number-of-padding-in-batch}
+\input{./Chapter6/Figures/figure-comparison-of-the-number-of-padding-in-batch}
 \caption{batch中padding数量对比（白色部分为padding）}
 \caption{batch中padding数量对比（白色部分为padding）}
 \label{fig:6-55}
 \label{fig:6-55}
 \end{figure}
 \end{figure}
@@ -1752,7 +1752,7 @@ Transformer Deep(48层) & 30.2            & 43.1            & 194$\times 10^{6}$
 % 图3.6.1
 % 图3.6.1
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Generate-summary}
+\input{./Chapter6/Figures/figure-generate-summary}
 \caption{文本自动摘要实例}
 \caption{文本自动摘要实例}
 \label{fig:6-57}
 \label{fig:6-57}
 \end{figure}
 \end{figure}
@@ -1764,7 +1764,7 @@ Transformer Deep(48层) & 30.2            & 43.1            & 194$\times 10^{6}$
 % 图3.6.1
 % 图3.6.1
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Example-of-automatic-translation-of-classical-Chinese}
+\input{./Chapter6/Figures/figure-example-of-automatic-translation-of-classical-chinese}
 \caption{文言文自动翻译实例}
 \caption{文言文自动翻译实例}
 \label{fig:6-58}
 \label{fig:6-58}
 \end{figure}
 \end{figure}
@@ -1780,7 +1780,7 @@ Transformer Deep(48层) & 30.2            & 43.1            & 194$\times 10^{6}$
 
 
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Automatically-generate-instances-of-couplets}
+\input{./Chapter6/Figures/figure-automatically-generate-instances-of-couplets}
 \caption{对联自动生成实例（人工给定上联）}
 \caption{对联自动生成实例（人工给定上联）}
 \label{fig:6-59}
 \label{fig:6-59}
 \end{figure}
 \end{figure}
@@ -1796,7 +1796,7 @@ Transformer Deep(48层) & 30.2            & 43.1            & 194$\times 10^{6}$
 
 
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter6/Figures/figure-Automatic-generation-of-ancient-poems-based-on-encoder-decoder-framework}
+\input{./Chapter6/Figures/figure-automatic-generation-of-ancient-poems-based-on-encoder-decoder-framework}
 \caption{基于编码器-解码器框架的古诗自动生成}
 \caption{基于编码器-解码器框架的古诗自动生成}
 \label{fig:6-60}
 \label{fig:6-60}
 \end{figure}
 \end{figure}

Book/Chapter7/Chapter7.tex

@@ -90,7 +90,7 @@
 %----------------------------------------------
 %----------------------------------------------
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/figure-construction-steps-of-MT-system}
+\input{./Chapter7/Figures/figure-construction-steps-of-mt-system}
 \caption{构建神经机器翻译系统的主要步骤}
 \caption{构建神经机器翻译系统的主要步骤}
 \label{fig:7-2}
 \label{fig:7-2}
 \end{figure}
 \end{figure}
@@ -417,7 +417,7 @@ y = f(x)
 % 图7.
 % 图7.
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/figure-Underfitting-vs-Overfitting}
+\input{./Chapter7/Figures/figure-underfitting-vs-overfitting}
 \caption{欠拟合 vs 过拟合}
 \caption{欠拟合 vs 过拟合}
 \label{fig:7-11}
 \label{fig:7-11}
 \end{figure}
 \end{figure}
@@ -1191,7 +1191,7 @@ b &=& \omega_{\textrm{high}}\cdot |\mathbf{x}|
 % 图7.5.1
 % 图7.5.1
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/Post-Norm-vs-Pre-Norm}
+\input{./Chapter7/Figures/figure-post-norm-vs-pre-norm}
 \caption{Post-Norm Transformer vs Pre-Norm Transformer}
 \caption{Post-Norm Transformer vs Pre-Norm Transformer}
 \label{fig:7-28}
 \label{fig:7-28}
 \end{figure}
 \end{figure}
@@ -1273,7 +1273,7 @@ $g_l$会作为输入的一部分送入第$l+1$层。其网络的结构图\ref{fi
 % 图7.5.2
 % 图7.5.2
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/dynamic-linear-aggregation-network-structure}
+\input{./Chapter7/Figures/figure-dynamic-linear-aggregation-network-structure}
 \caption{动态线性层聚合网络结构图}
 \caption{动态线性层聚合网络结构图}
 \label{fig:7-29}
 \label{fig:7-29}
 \end{figure}
 \end{figure}
@@ -1299,7 +1299,7 @@ $g_l$会作为输入的一部分送入第$l+1$层。其网络的结构图\ref{fi
 % 图7.5.3
 % 图7.5.3
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/progressive-training}
+\input{./Chapter7/Figures/figure-progressive-training}
 \caption{渐进式深层网络训练过程}
 \caption{渐进式深层网络训练过程}
 \label{fig:7-30}
 \label{fig:7-30}
 \end{figure}
 \end{figure}
@@ -1316,7 +1316,7 @@ $g_l$会作为输入的一部分送入第$l+1$层。其网络的结构图\ref{fi
 % 图7.5.4
 % 图7.5.4
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/sparse-connections-between-different-groups}
+\input{./Chapter7/Figures/figure-sparse-connections-between-different-groups}
 \caption{不同组之间的稀疏连接}
 \caption{不同组之间的稀疏连接}
 \label{fig:7-31}
 \label{fig:7-31}
 \end{figure}
 \end{figure}
@@ -1335,7 +1335,7 @@ $g_l$会作为输入的一部分送入第$l+1$层。其网络的结构图\ref{fi
 % 图7.5.5
 % 图7.5.5
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/learning-rate}
+\input{./Chapter7/Figures/figure-learning-rate}
 \caption{学习率重置vs从头训练的学习率曲线}
 \caption{学习率重置vs从头训练的学习率曲线}
 \label{fig:7-32}
 \label{fig:7-32}
 \end{figure}
 \end{figure}
@@ -1411,7 +1411,7 @@ p_l=\frac{l}{2L}\cdot \varphi
 % 图7.5.7
 % 图7.5.7
 \begin{figure}[htp]
 \begin{figure}[htp]
 \centering
 \centering
-\input{./Chapter7/Figures/expanded-residual-network}
+\input{./Chapter7/Figures/figure-expanded-residual-network}
 \caption{Layer Dropout中残差网络的展开图}
 \caption{Layer Dropout中残差网络的展开图}
 \label{fig:7-34}
 \label{fig:7-34}
 \end{figure}
 \end{figure}

Book/mt-book-xelatex.tex

@@ -122,13 +122,13 @@
 %	CHAPTERS
 %	CHAPTERS
 %----------------------------------------------------------------------------------------
 %----------------------------------------------------------------------------------------
 
 
-\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}