合并分支 'master' 到 'mengxia'

Master

查看合并请求 !492

Chapter1/chapter1.tex

@@ -99,7 +99,7 @@
 \end{figure}
 %------------------------------------------
 
-\parinterval 在此之后，更多的翻译工作在文化和知识传播中开展。其中一个典型代表是宗教文献的翻译。宗教是人类意识形态的一个重要载体，为了宣传教义，人们编写了大量的宗教文献。在西方，一项最早被记录的翻译活动是将旧约圣经（希伯来文及埃兰文）翻译为希腊文版本。迄今为止人类历史上翻译版本最多的书就是圣经。在中国唐代，有一位世界性的文化人物\ \dash \ 玄奘，他不仅是佛学家、旅行家，还是翻译家。玄奘西行求法归来后把全部的心血和智慧奉献给了译经事业，在助手们的帮助下，共翻译佛教经论74部，1335卷，每卷万字左右，合计1335万字，占去整个唐代译经总数的一半以上\upcite{慧立彦宗1983大慈恩寺三藏法师传}，树立了我国古代翻译思想的光辉典范。
+\parinterval 在此之后，更多的翻译工作在文化和知识传播中开展。其中一个典型代表是宗教文献的翻译。宗教是人类意识形态的一个重要载体，为了宣传教义，人们编写了大量的宗教文献。在西方，一项最早被记录的翻译活动是将旧约圣经（希伯来文及埃兰文）翻译为希腊文版本。迄今为止人类历史上翻译版本最多的书就是圣经。在中国唐代，有一位世界性的文化人物\ \dash \ 玄奘，他不仅是佛学家、旅行家，还是翻译家。玄奘西行求法归来后把全部的心血和智慧奉献给了译经事业，在助手们的帮助下，共翻译佛教经论74部，1335卷，每卷万字左右，合计1335万字，占去整个唐代译经总数的一半以上\upcite{慧立2000大慈恩寺三藏法師傳}，树立了我国古代翻译思想的光辉典范。
 
 \parinterval 翻译在人类历史长河中起到了重要的作用。一方面，由于语言文字、文化和地理位置的差异性，使得翻译成为一个重要的需求；另一方面，翻译也加速了不同文明的融会贯通，促进了世界的发展。今天，翻译已经成为重要的行业之一，包括各个高校也都设立了翻译及相关专业，相关人才不断涌现。据《2019年中国语言服务行业发展报告》\upcite{2019cns}统计：全球语言服务产值预计将首次接近500亿美元；中国涉及语言服务的在营企业360,000余家，语言服务为主营业务的在营企业近万家，总产值超过300亿元，年增长3\%以上；全国开设外语类专业的高校数量多达上千所，其中设立有翻译硕士（MTI）和翻译本科（BTI）专业的院校分别有250余所和280余所，其中仅MTI的累计招生数就高达6万余人\upcite{赵军峰2019深化改革}。当然，面对着巨大的需求，如何使用机器辅助翻译等技术手段提高人工翻译效率，也是人工翻译和机器翻译领域需要共同探索的方向。
 

Chapter10/Figures/figure-3-base-problom-of-p.tex

@@ -12,7 +12,7 @@
 				% RNN Encoder
 				\coordinate (eemb0) at (0,0);
 				\foreach \x [count=\y from 0] in {1,2,...,3}
-					\node[rnnnode,minimum height=0.5\base,fill=green!30!white,anchor=west] (eemb\x) at ([xshift=0.4\base]eemb\y.east) {\tiny{$e_x()$}};
+					\node[rnnnode,minimum height=0.5\base,fill=green!30!white,anchor=west] (eemb\x) at ([xshift=0.4\base]eemb\y.east) {\tiny{$\textrm{e}_x()$}};
 				\foreach \x in {1,2,...,3}
 					\node[rnnnode,fill=blue!30!white,anchor=south] (enc\x) at ([yshift=0.3\base]eemb\x.north) {};
 			        \node[] (enclabel1) at (enc1) {\tiny{$\mathbi{h}_{m-2}$}};
@@ -27,7 +27,7 @@
 	
 				% RNN Decoder
 				\foreach \x in {1,2,...,3}
-					\node[rnnnode,minimum height=0.5\base,fill=green!30!white,anchor=south] (demb\x) at ([yshift=\base]enc\x.north) {\tiny{$e_y()$}};
+					\node[rnnnode,minimum height=0.5\base,fill=green!30!white,anchor=south] (demb\x) at ([yshift=\base]enc\x.north) {\tiny{$\textrm{e}_y()$}};
 				\foreach \x in {1,2,...,3}
 					\node[rnnnode,fill=blue!30!white,anchor=south] (dec\x) at ([yshift=0.3\base]demb\x.north) {{\tiny{$\mathbi{s}_\x$}}};
 				\foreach \x in {1,2,...,3}
@@ -80,10 +80,10 @@
 				}
 				
 				{
-				\node [anchor=north west] (line11) at ([yshift=-1.8em]line4.west) {\scriptsize{每个词的one-hot}};
+				\node [anchor=north west] (line11) at ([yshift=-1.8em]line4.west) {\scriptsize{每个词的One-hot}};
 				\node [anchor=north west] (line12) at ([yshift=0.3em]line11.south west) {\scriptsize{离散化表示都被转化为\ \ \ \ }};
 				\node [anchor=north west] (line13) at ([yshift=0.3em]line12.south west) {\scriptsize{实数向量，即词嵌入}};
-				\node [anchor=north west] (line14) at ([yshift=0.3em]line13.south west) {\scriptsize{($e_x()$和$e_y()$函数)}};
+				\node [anchor=north west] (line14) at ([yshift=0.3em]line13.south west) {\scriptsize{($\textrm{e}_x()$和$\textrm{e}_y()$函数)}};
 				}
 				
 				{

Chapter10/Figures/figure-bi-rnn.tex

@@ -43,7 +43,7 @@
                 \node[rnnnode,minimum height=0.5\base,fill=red!30!white,anchor=south] (softmax\x) at ([yshift=0.5\base]dec\x.north) {};
 
             % Decoder input words
-            \node[wordnode,below=0pt of demb1] (decwordin) {$\langle$eos$\rangle$};
+            \node[wordnode,below=0pt of demb1] (decwordin) {$\langle$sos$\rangle$};
             \ExtractX{$(demb2.south)$}
             \ExtractY{$(decwordin.base)$}
             \node[wordnode,anchor=base] () at (\XCoord,\YCoord) {Do};

Chapter10/Figures/figure-gru01.tex

@@ -83,10 +83,10 @@
             
         \end{scope}
 
-       \node[] (tanh) at (aux46){};
+       \node[] (Tanh) at (aux46){};
 
         \begin{pgfonlayer}{background}
-            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (tanh)] (GRU) {};
+            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (Tanh)] (GRU) {};
         \end{pgfonlayer}
 
 

Chapter10/Figures/figure-gru02.tex

@@ -96,10 +96,10 @@
             
         \end{scope}
         
-        \node[] (tanh) at (aux46){};
+        \node[] (Tanh) at (aux46){};
 
         \begin{pgfonlayer}{background}
-            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (tanh)] (GRU) {};
+            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (Tanh)] (GRU) {};
         \end{pgfonlayer}
 
 

Chapter10/Figures/figure-gru03.tex

@@ -99,7 +99,7 @@
                 \draw[-latex,emph] (aux71) -| (aux87);
                 \draw[-latex,emph] (aux71) -| (aux53) -- (aux23) -| (aux46) -- (z76);
                 \draw[emph] (aux12) |- (aux23) -| (aux46);
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] (tanh) at (aux46) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] (Tanh) at (aux46) {$\mathrm{Tanh}$};
                 \node[opnode,circle,draw=red,thick] (a1) at (aux53) {};
                 \node[opnode,circle,draw=red,thick] (a2) at (aux56) {};
                 \node[opnode,circle,draw=red,thick] (a3) at (aux75) {};
@@ -118,7 +118,7 @@
         \end{scope}
 
         \begin{pgfonlayer}{background}
-            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (tanh)] (GRU) {};
+            \node[draw,very thick,rectangle,fill=blue!10!white,rounded corners=5pt,inner sep=6pt,fit=(aux22) (aux76) (z76) (Tanh)] (GRU) {};
         \end{pgfonlayer}
         
         %%new

Chapter10/Figures/figure-lstm02.tex

@@ -93,7 +93,7 @@
                 \draw[-latex,emph] (aux21) -- (aux25) -- (u55);
                 \draw[emph] (aux12) -- (aux22) -- (aux23);
                 \node[opnode,circle,draw=red,thick] () at (aux34) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{Tanh}$};
                 \node[opnode,circle,draw=red,thick] (i45) at (aux45) {};
             }
          \end{scope}

Chapter10/Figures/figure-lstm03.tex

@@ -92,7 +92,7 @@
                 \draw[-latex,emph] (aux21) -- (aux25) -- (u55);
                 \draw[emph] (aux12) -- (aux22) -- (aux23);
                 \node[opnode,circle,draw=red,thick] () at (aux34) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{Tanh}$};
                 \node[opnode,circle,draw=red,thick] (i45) at (aux45) {X};
             }
             {
@@ -100,7 +100,7 @@
                 \draw[-latex,standard] (aux21) -- (aux24) |- (i45);
                 \draw[-latex,standard] (aux21) -- (aux25) -- (u55);
                 \node[opnode,circle] () at (aux34) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{Tanh}$};
                 \node[opnode,circle] (i45) at (aux45) {};
             }
             % cell update

Chapter10/Figures/figure-lstm04.tex

@@ -93,7 +93,7 @@
                 \draw[-latex,emph] (aux21) -- (aux25) -- (u55);
                 \draw[emph] (aux12) -- (aux22) -- (aux23);
                 \node[opnode,circle,draw=red,thick] () at (aux34) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{Tanh}$};
                 \node[opnode,circle,draw=red,thick] (i45) at (aux45) {X};
             }
             {
@@ -101,7 +101,7 @@
                 \draw[-latex,standard] (aux21) -- (aux24) |- (i45);
                 \draw[-latex,standard] (aux21) -- (aux25) -- (u55);
                 \node[opnode,circle] () at (aux34) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{Tanh}$};
                 \node[opnode,circle] (i45) at (aux45) {};
             }
             % cell update
@@ -122,7 +122,7 @@
                 \draw[-latex,emph] (aux21) -- (o27);
                 \draw[emph] (aux12) -- (aux22) -- (aux23);
                 \node[opnode,circle,draw=red,thick] () at (aux26) {$\sigma$};
-                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux37) {$\mathrm{tanh}$};
+                \node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux37) {$\mathrm{Tanh}$};
 
                 \draw[-latex,emph] (o27) -- (aux29);
                 \draw[-latex,emph] (o27) -| (aux68);

Chapter10/Figures/figure-the-whole-of-lstm.tex

@@ -94,7 +94,7 @@
 \draw[-latex,emph] (aux21) -- (aux25) -- (u55);
 \draw[emph] (aux12) -- (aux22) -- (aux23);
 \node[opnode,circle,draw=red,thick] () at (aux34) {$\sigma$};
-\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{tanh}$};
+\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux35) {$\mathrm{Tanh}$};
 \node[opnode,circle,draw=red,thick] (i45) at (aux45) {};
 }
 {
@@ -102,7 +102,7 @@
 \draw[-latex,standard] (aux21) -- (aux24) |- (i45);
 \draw[-latex,standard] (aux21) -- (aux25) -- (u55);
 \node[opnode,circle] () at (aux34) {$\sigma$};
-\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{tanh}$};
+\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux35) {$\mathrm{Tanh}$};
 \node[opnode,circle] (i45) at (aux45) {};
 }
 % cell update
@@ -123,7 +123,7 @@
 \draw[-latex,emph] (aux21) -- (o27);
 \draw[emph] (aux12) -- (aux22) -- (aux23);
 \node[opnode,circle,draw=red,thick] () at (aux26) {$\sigma$};
-\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux37) {$\mathrm{tanh}$};
+\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt,draw=red,thick] () at (aux37) {$\mathrm{Tanh}$};
 
 \draw[-latex,emph] (o27) -- (aux29);
 \draw[-latex,emph] (o27) -| (aux68);
@@ -133,7 +133,7 @@
 \draw[-latex,standard] (u55) -| (o27);
 \draw[-latex,standard] (aux21) -- (o27);
 \node[opnode,circle] () at (aux26) {$\sigma$};
-\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux37) {$\mathrm{tanh}$};
+\node[opnode,rectangle,rounded corners=2pt,inner sep=2pt] () at (aux37) {$\mathrm{Tanh}$};
 
 \draw[-latex,standard] (o27) -- (aux29);
 \draw[-latex,standard] (o27) -| (aux68);
@@ -174,7 +174,7 @@
 }
 {
 % input gate formula
-\node[formulanode,anchor=north east,text width=10em] () at ([shift={(4\base,-1.5\base)}]aux21) {输入门\\$\mathbi{i}_t=\sigma(\mathbi{W}_i[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_i)$\\$\hat{\mathbi{c}}_t=\mathrm{tanh}(\mathbi{W}_c[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_c)$};
+\node[formulanode,anchor=north east,text width=10em] () at ([shift={(4\base,-1.5\base)}]aux21) {输入门\\$\mathbi{i}_t=\sigma(\mathbi{W}_i[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_i)$\\$\hat{\mathbi{c}}_t=\mathrm{Tanh}(\mathbi{W}_c[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_c)$};
 }
 {
 % cell update formula
@@ -182,7 +182,7 @@
 }
 {
 % output gate formula
-\node[formulanode,anchor=north west,text width=10em] () at ([shift={(-4\base,-1.5\base)}]aux29) {输出门\\$\mathbi{o}_t=\sigma(\mathbi{W}_o[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_o)$\\$\mathbi{h}_{t}=\mathbi{o}_t\cdot \mathrm{tanh}(\mathbi{c}_{t})$};
+\node[formulanode,anchor=north west,text width=10em] () at ([shift={(-4\base,-1.5\base)}]aux29) {输出门\\$\mathbi{o}_t=\sigma(\mathbi{W}_o[\mathbi{h}_{t-1},\mathbi{x}_t]+\mathbi{b}_o)$\\$\mathbi{h}_{t}=\mathbi{o}_t\cdot \mathrm{Tanh}(\mathbi{c}_{t})$};
 }
 \end{scope}
 \end{tikzpicture}

Chapter11/Figures/figure-average-pooling.tex

@@ -2,29 +2,32 @@
 
 
 \begin{tikzpicture}[node distance = 0cm]
-\node(num1)[num,fill=red!10]{0};
-\node(num2)[num,below of = num1,yshift= -0.6cm,fill=red!10]{0};
+\node(num1)[num,fill=red!10]{1};
+\node(num2)[num,below of = num1,yshift= -0.6cm,fill=red!10]{5};
 \node(num3)[num,right of = num1,xshift= 0.6cm,fill=red!10]{0};
-\node(num4)[num,below of = num3,yshift= -0.6cm,fill=red!10]{0};
-\node(num5)[num,right of = num3,xshift= 0.6cm,fill=green!10]{1};
-\node(num6)[num,below of = num5,yshift= -0.6cm,fill=green!10]{3};
-\node(num7)[num,right of = num5,xshift= 0.6cm,fill=green!10]{3};
-\node(num8)[num,below of = num7,yshift= -0.6cm,fill=green!10]{1};
-\node(num9)[num,below of = num2,yshift= -0.6cm,fill=yellow!10]{7};
-\node(num10)[num,below of = num9,yshift= -0.6cm,fill=yellow!10]{7};
-\node(num11)[num,right of = num9,xshift= 0.6cm,fill=yellow!10]{6};
-\node(num12)[num,below of = num11,yshift= -0.6cm,fill=yellow!10]{8};
-\node(num13)[num,right of = num11,xshift= 0.6cm,fill=blue!10]{3};
+\node(num4)[num,below of = num3,yshift= -0.6cm,fill=red!10]{6};
+
+\node(num5)[num,right of = num3,xshift= 0.6cm,fill=green!10]{4};
+\node(num6)[num,below of = num5,yshift= -0.6cm,fill=green!10]{7};
+\node(num7)[num,right of = num5,xshift= 0.6cm,fill=green!10]{5};
+\node(num8)[num,below of = num7,yshift= -0.6cm,fill=green!10]{8};
+
+\node(num9)[num,below of = num2,yshift= -0.6cm,fill=yellow!10]{3};
+\node(num10)[num,below of = num9,yshift= -0.6cm,fill=yellow!10]{1};
+\node(num11)[num,right of = num9,xshift= 0.6cm,fill=yellow!10]{2};
+\node(num12)[num,below of = num11,yshift= -0.6cm,fill=yellow!10]{2};
+
+\node(num13)[num,right of = num11,xshift= 0.6cm,fill=blue!10]{1};
 \node(num14)[num,below of = num13,yshift= -0.6cm,fill=blue!10]{3};
-\node(num10)[num,right of = num13,xshift= 0.6cm,fill=blue!10]{2};
+\node(num10)[num,right of = num13,xshift= 0.6cm,fill=blue!10]{0};
 \node(num16)[num,below of = num10,yshift= -0.6cm,fill=blue!10]{4};
 
 \draw[->,thick]([xshift=0.4cm,yshift=-0.4cm]num8.east)--([xshift=1.5cm,yshift=-0.4cm]num8.east);
 
-\node(num17)[num,right of = num8,xshift= 2.5cm,fill=red!10]{0};
-\node(num18)[num,right of = num17,xshift= 0.6cm,fill=green!10]{2};
-\node(num19)[num,below of = num17,yshift=-0.6cm,fill=yellow!10]{7};
-\node(num20)[num,below of = num18,yshift= -0.6cm,fill=blue!10]{3};
+\node(num17)[num,right of = num8,xshift= 2.5cm,fill=red!10]{3};
+\node(num18)[num,right of = num17,xshift= 0.6cm,fill=green!10]{6};
+\node(num19)[num,below of = num17,yshift=-0.6cm,fill=yellow!10]{2};
+\node(num20)[num,below of = num18,yshift= -0.6cm,fill=blue!10]{2};
 
 \node [right of = num2,xshift= -0.7cm]{};
 

Chapter11/Figures/figure-fairseq-0.tex

@@ -43,7 +43,7 @@
 	\node [draw=ugreen!30,rectangle,inner ysep=5pt,inner xsep=1.8em,rounded corners=4pt,line width=2pt,fill=ugreen!10] [fit = (tgt_1) (i_0)(tgt_2)(i_5) ] (group1_2) {};
   \end{pgfonlayer}
 
-\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{目标语词嵌入}};
 \node[anchor=south, word] (l_1) at ([yshift=2em]l_0.north){\sffamily\bfnew{卷积}};
 \node[anchor=south, word] (l_2) at ([yshift=2.4em]l_1.north){\sffamily\bfnew{门控}};
 \node[anchor=south, word] (l_3) at ([yshift=0.06em]l_2.north){\sffamily\bfnew{线性单元}};
@@ -144,7 +144,7 @@
 \node[anchor=south,word] (src_2) at ([xshift=2em,yshift=0.4em]r_2.north){$<$p$>$};
 
 
-\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{源语词嵌入}};
 \node[anchor=north, word] (t_2) at ([yshift=-2em]t_1.south){\sffamily\bfnew{卷积}};
 \node[anchor=north, word] (t_3) at ([yshift=-2.8em]t_2.south){\sffamily\bfnew{门控}};
 \node[anchor=north, word] (t_4) at ([yshift=-0.06em]t_3.south){\sffamily\bfnew{线性单元}};

Chapter11/Figures/figure-fairseq-2.tex

@@ -39,7 +39,7 @@
 \node[anchor=north,word] at ([yshift=-0.4em]i_4.south){to};
 \node[anchor=north,word] at ([yshift=-0.4em]i_5.south){school};
 
-\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{目标语词嵌入}};
 \node[anchor=south, word] (l_1) at ([yshift=2em]l_0.north){\sffamily\bfnew{卷积}};
 \node[anchor=south, word] (l_2) at ([yshift=2.4em]l_1.north){\sffamily\bfnew{门控}};
 \node[anchor=south, word] (l_3) at ([yshift=0.06em]l_2.north){\sffamily\bfnew{线性单元}};
@@ -139,7 +139,7 @@
 \node[anchor=south,word] (src_2) at ([xshift=2em,yshift=0.4em]r_2.north){$<$p$>$};
 
 
-\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{源语词嵌入}};
 \node[anchor=north, word] (t_2) at ([yshift=-2em]t_1.south){\sffamily\bfnew{卷积}};
 \node[anchor=north, word] (t_3) at ([yshift=-2.8em]t_2.south){\sffamily\bfnew{门控}};
 \node[anchor=north, word] (t_4) at ([yshift=-0.06em]t_3.south){\sffamily\bfnew{线性单元}};

Chapter11/Figures/figure-fairseq-3.tex

@@ -39,7 +39,7 @@
 \node[anchor=north,word] at ([yshift=-0.4em]i_4.south){to};
 \node[anchor=north,word] at ([yshift=-0.4em]i_5.south){school};
 
-\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (l_0) at ([xshift=-2em,yshift=-0.5em]i_0.west){\sffamily\bfnew{目标语词嵌入}};
 \node[anchor=south, word] (l_1) at ([yshift=2em]l_0.north){\sffamily\bfnew{卷积}};
 \node[anchor=south, word] (l_2) at ([yshift=2.4em]l_1.north){\sffamily\bfnew{门控}};
 \node[anchor=south, word] (l_3) at ([yshift=0.06em]l_2.north){\sffamily\bfnew{线性单元}};
@@ -140,7 +140,7 @@
 \node[anchor=south,word] (src_2) at ([xshift=2em,yshift=0.4em]r_2.north){$<$p$>$};
 
 
-\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{词嵌入}};
+\node[anchor=east, word] (t_1) at ([xshift=-4em,yshift=0.5em]r_0.west){\sffamily\bfnew{源语词嵌入}};
 \node[anchor=north, word] (t_2) at ([yshift=-2em]t_1.south){\sffamily\bfnew{卷积}};
 \node[anchor=north, word] (t_3) at ([yshift=-2.8em]t_2.south){\sffamily\bfnew{门控}};
 \node[anchor=north, word] (t_4) at ([yshift=-0.06em]t_3.south){\sffamily\bfnew{线性单元}};

Chapter11/Figures/figure-image-convolution.tex

@@ -25,9 +25,9 @@
 	\node[data,inner sep=2pt,fill=cyan!40] at (14.4em,2.4em) {19};
 	\node[data,inner sep=2pt] at (16em,2.4em) {25};
 	
-	\node[font=\footnotesize] (in) at (1.6em,4.8em) {输入};
-	\node[font=\footnotesize] at (8.8em,4.8em) {卷积核};
-	\node[font=\footnotesize] (out) at (15.2em,4.8em) {输出};
+	\node[font=\footnotesize] (in) at (1.6em,-1.8em) {输入：$3\times 3$};
+	\node[font=\footnotesize] at (8.8em,-1.8em) {卷积核：$2\times 2$};
+	\node[font=\footnotesize] (out) at (15.2em,-1.8em) {输出：$2\times 2$};
 
 	%\node[font=\footnotesize,dashed,draw=cyan,very thick,fill=cyan!5,align=center] at ([yshift=-0.3cm,xshift=1.8cm]out.east) {*\ \ ：表示\\卷积计算};
 	%\node[] at ([yshift=-0.3cm,xshift=-2.3cm]in.east) {\ \ \ \ \ };

Chapter11/Figures/figure-max-pooling.tex

@@ -4,16 +4,19 @@
 \begin{tikzpicture}[node distance = 0cm]
 \node(num1)[num,fill=red!10]{1};
 \node(num2)[num,below of = num1,yshift= -0.6cm,fill=red!10]{5};
-\node(num3)[num,right of = num1,xshift= 0.6cm,fill=red!10]{1};
+\node(num3)[num,right of = num1,xshift= 0.6cm,fill=red!10]{0};
 \node(num4)[num,below of = num3,yshift= -0.6cm,fill=red!10]{6};
-\node(num5)[num,right of = num3,xshift= 0.6cm,fill=green!10]{2};
+
+\node(num5)[num,right of = num3,xshift= 0.6cm,fill=green!10]{4};
 \node(num6)[num,below of = num5,yshift= -0.6cm,fill=green!10]{7};
-\node(num7)[num,right of = num5,xshift= 0.6cm,fill=green!10]{4};
+\node(num7)[num,right of = num5,xshift= 0.6cm,fill=green!10]{5};
 \node(num8)[num,below of = num7,yshift= -0.6cm,fill=green!10]{8};
+
 \node(num9)[num,below of = num2,yshift= -0.6cm,fill=yellow!10]{3};
 \node(num10)[num,below of = num9,yshift= -0.6cm,fill=yellow!10]{1};
 \node(num11)[num,right of = num9,xshift= 0.6cm,fill=yellow!10]{2};
 \node(num12)[num,below of = num11,yshift= -0.6cm,fill=yellow!10]{2};
+
 \node(num13)[num,right of = num11,xshift= 0.6cm,fill=blue!10]{1};
 \node(num14)[num,below of = num13,yshift= -0.6cm,fill=blue!10]{3};
 \node(num10)[num,right of = num13,xshift= 0.6cm,fill=blue!10]{0};

Chapter11/Figures/figure-use-cnn-in-sentence-classification.tex

@@ -8,56 +8,54 @@
 	\tikzstyle{cir} = [thin,fill=blue!8,draw,circle,minimum size =0.5em,drop shadow={shadow xshift=0.15em, shadow yshift=-0.1em}]
 	\tikzstyle{word} = [inner sep=0pt, font=\footnotesize,minimum height=\bcc]
 	
-	\draw[fill=blue!8,xshift=0.3cm,yshift=0.5cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+9*\bcc);
-	\draw[ugreen!60,step=\bcc,xshift=0.3cm,yshift=0.5cm,gray] (0cm,0cm) grid (0cm+6*\bcc,0cm+9*\bcc); 
-	%\draw[line width=0.7pt,xshift=0.3cm,yshift=0.5cm] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+9*\bcc);
-	\draw[red!60,line width=2pt,xshift=0.3cm,yshift=0.5cm] (0cm,0cm+2*\bcc) rectangle (0cm+6*\bcc,0cm+4*\bcc);
-	
+	%\draw[fill=blue!8,xshift=0.3cm,yshift=0.5cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+9*\bcc);
+	%\draw[ugreen!60,step=\bcc,xshift=0.3cm,yshift=0.5cm,gray] (0cm,0cm) grid (0cm+6*\bcc,0cm+9*\bcc); 
+	%\draw[red!60,line width=2pt,xshift=0.3cm,yshift=0.5cm] (0cm,0cm+2*\bcc) rectangle (0cm+6*\bcc,0cm+4*\bcc);
 	
+	% 输入矩阵
 	\draw[thick,fill=blue!8,line width=0.6pt] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+9*\bcc);
 	\draw[step=\bcc,gray] (0cm,0cm) grid (0cm+6*\bcc,0cm+9*\bcc); 
-	%\draw[line width=0.7pt] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+9*\bcc);
 	\draw[red!60,line width=2pt] (0cm,0cm) rectangle (0cm+6*\bcc,0cm+2*\bcc);
 	\draw[ugreen!60,line width=2pt] (0cm,0cm+3*\bcc) rectangle (0cm+6*\bcc,0cm+6*\bcc);
 	\draw[red!60,line width=2pt] (0cm,0cm+7*\bcc) rectangle (0cm+6*\bcc,0cm+9*\bcc);
 
-	
-	\draw[fill=blue!8,xshift=5.0cm,yshift=1.3cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+6*\bcc);
-	\draw[step=\bcc,gray,xshift=5.0cm,yshift=1.3cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+6*\bcc);
-	%\draw[xshift=5.0cm,yshift=1.3cm,line width=0.7pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+6*\bcc);
+	% 特征图
+	\draw[fill=blue!8,xshift=5.0cm,yshift=1.3cm,line width=0.6pt] (0cm,0cm-1*\bcc) rectangle (0cm+1*\bcc,0cm+6*\bcc);
+	\draw[step=\bcc,gray,xshift=5.0cm,yshift=1.3cm] (0cm,0cm-1*\bcc) grid (0cm+1*\bcc,0cm+6*\bcc);
 	\draw[ugreen!60,line width=2pt,xshift=5.0cm,yshift=1.3cm] (0cm,0cm+2*\bcc) rectangle (0cm+1*\bcc,0cm+3*\bcc);
 	
-	\draw [gray,fill=blue!8,line width=0.6pt](8cm,2.6cm) -- (8.4cm, 2.6cm) -- (9cm,1cm) -- (8.6cm, 1cm) -- (8cm,2.6cm);
-	\draw [gray](8.15cm,2.2cm) -- (8.55cm,2.2cm);
-	\draw [gray](8.3cm,1.8cm) -- (8.7cm,1.8cm);
-	\draw [gray](8.45cm,1.4cm) -- (8.85cm,1.4cm);
+	%最大池化
+	\draw [gray,fill=blue!8,line width=0.6pt](8cm,2.2cm) -- (8.4cm, 2.2cm) -- (8.7cm,1.4cm) -- (8.3cm, 1.4cm) -- (8cm,2.2cm);
+	\draw [gray](8.15cm,1.8cm) -- (8.55cm,1.8cm);
+	%\draw [gray](8.3cm,1.8cm) -- (8.7cm,1.8cm);
+	%\draw [gray](8.45cm,1.4cm) -- (8.85cm,1.4cm);
 	
-	\draw [gray,fill=blue!8,line width=0.6pt](11cm,2.2cm) -- (11.4cm, 2.2cm) -- (11.7cm,1.4cm) -- (11.3cm, 1.4cm) -- (11cm,2.2cm);
-	\draw [gray](11.15cm,1.8cm) -- (11.55cm,1.8cm);
+	%全连接层
+	\draw [gray,fill=blue!8,line width=0.6pt](11cm,2.2cm) -- (11.4cm, 2.2cm) -- (11.7cm,1.8cm) -- (11.3cm, 1.8cm) -- (11cm,2.2cm);
+	%\draw [gray](11.15cm,1.8cm) -- (11.55cm,1.8cm);
 	
-	\draw[ugreen!60,line] ([xshift=5.0cm,yshift=1.3cm]0cm+1*\bcc,0cm+6*\bcc) -- (8cm,2.6cm);
-	\draw[ugreen!60,line] ([xshift=5.0cm,yshift=1.3cm]0cm+1*\bcc,0cm) -- (8.15cm,2.2cm);
+	%最大池化
+	\draw[ugreen!60,line] ([xshift=5.0cm,yshift=1.3cm]0cm+1*\bcc,0cm+6*\bcc) -- (8cm,2.2cm);
+	\draw[ugreen!60,line] ([xshift=5.0cm,yshift=1.3cm]0cm+1*\bcc,0cm-1*\bcc) -- (8.15cm,1.8cm);
 
-	\draw[fill=blue!8,xshift=5.2cm,yshift=1.0cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+6*\bcc);
-	\draw[step=\bcc,gray,xshift=5.2cm,yshift=1.0cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+6*\bcc); 
-	%\draw[line width=0.7pt,xshift=5.2cm,yshift=1.0cm] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+6*\bcc);
+	%特征图
+	%\draw[fill=blue!8,xshift=5.2cm,yshift=1.0cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+6*\bcc);
+	%\draw[step=\bcc,gray,xshift=5.2cm,yshift=1.0cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+6*\bcc); 
 	
-	\draw[fill=blue!8,xshift=5.4cm,yshift=0.3cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+7*\bcc);
-	\draw[step=\bcc,gray,xshift=5.4cm,yshift=0.3cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+7*\bcc);
-	%\draw[line width=0.7pt,xshift=5.4cm,yshift=0.3cm] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+7*\bcc); 
+	%\draw[fill=blue!8,xshift=5.4cm,yshift=0.3cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+7*\bcc);
+	%\draw[step=\bcc,gray,xshift=5.4cm,yshift=0.3cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+7*\bcc);
 	
-	\draw[fill=blue!8,xshift=5.6cm,yshift=0cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+7*\bcc);
-	\draw[step=\bcc,gray,xshift=5.6cm,yshift=0cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+7*\bcc); 
-	%\draw[line width=0.7pt,xshift=5.6cm,yshift=0cm] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+7*\bcc);
+	\draw[fill=blue!8,xshift=5.6cm,yshift=0cm,line width=0.6pt] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+8*\bcc);
+	\draw[step=\bcc,gray,xshift=5.6cm,yshift=0cm] (0cm,0cm) grid (0cm+1*\bcc,0cm+8*\bcc); 
 	\draw[red!60,line width=2pt,xshift=5.6cm,yshift=0cm] (0cm,0cm) rectangle (0cm+1*\bcc,0cm+1*\bcc);
-	\draw[red!60,line width=2pt,xshift=5.6cm,yshift=0cm] (0cm,0cm+2*\bcc) rectangle (0cm+1*\bcc,0cm+3*\bcc);
-	\draw[red!60,line width=2pt,xshift=5.6cm,yshift=0cm] (0cm,0cm+6*\bcc) rectangle (0cm+1*\bcc,0cm+7*\bcc);
+	\draw[red!60,line width=2pt,xshift=5.6cm,yshift=0cm] (0cm,0cm+7*\bcc) rectangle (0cm+1*\bcc,0cm+8*\bcc);
 	
-	\draw[line] (8.4cm, 2.6cm) -- (11cm,2.2cm);
-	\draw[line] (9cm,1cm) -- (11.3cm, 1.4cm);
+	% 全连接线
+	\draw[line] (8.4cm, 2.2cm) -- (11.2cm,2.2cm);
+	\draw[line] (8.7cm,1.4cm) -- (11.3cm, 1.8cm);
 	
-	\draw[red!60,line] ([xshift=5.6cm,yshift=0cm]0cm+1*\bcc,0cm+7*\bcc) -- (8.45cm,1.4cm);
-	\draw[red!60,line] ([xshift=5.6cm,yshift=0cm]0cm+1*\bcc,0cm) -- (8.6cm, 1cm);
+	\draw[red!60,line] ([xshift=5.6cm,yshift=0cm]0cm+1*\bcc,0cm+7*\bcc) -- (8.15cm,1.8cm);
+	\draw[red!60,line] ([xshift=5.6cm,yshift=0cm]0cm+1*\bcc,0cm) -- (8.25cm, 1.4cm);
 	
 	\draw[red!60,line] (0cm+6*\bcc,0cm+9*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+7*\bcc);
 	\draw[red!60,line] (0cm+6*\bcc,0cm+7*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+6*\bcc);
@@ -65,8 +63,8 @@
 	\draw[red!60,line] (0cm+6*\bcc,0cm) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm);
 	\draw[ugreen!60,line] (0cm+6*\bcc,0cm+6*\bcc) -- ([xshift=5.0cm,yshift=1.3cm]0cm,0cm+3*\bcc);
 	\draw[ugreen!60,line] (0cm+6*\bcc,0cm+3*\bcc) -- ([xshift=5.0cm,yshift=1.3cm]0cm,0cm+2*\bcc);
-	\draw[red!60,line] ([xshift=0.3cm,yshift=0.5cm]0cm+6*\bcc,0cm+4*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+3*\bcc);
-	\draw[red!60,line] ([xshift=0.3cm,yshift=0.5cm]0cm+6*\bcc,0cm+2*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+2*\bcc);
+	%\draw[red!60,line] ([xshift=0.3cm,yshift=0.5cm]0cm+6*\bcc,0cm+4*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+3*\bcc);
+	%\draw[red!60,line] ([xshift=0.3cm,yshift=0.5cm]0cm+6*\bcc,0cm+2*\bcc) -- ([xshift=5.6cm,yshift=0cm]0cm,0cm+2*\bcc);
 	
 	\node[word] (w1) at (-0.5cm, 3.4cm) {wait};
 	\node[word] (w2) at ([yshift=-\bcc]w1) {for};
@@ -81,18 +79,13 @@
 	\node[draw,rectangle callout,callout relative pointer={(0.28,-0.6)}] at (-0.3cm,4.6cm) {\textrm{卷积核}};
 	\node[draw,rectangle callout,callout relative pointer={(0.1,-0.5)}] at (5cm,4.6cm) {\textrm{特征图}};
 
-	%\draw [thick] (0cm, -0.3cm) -- (0cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{$m \times k$ representation of \\ sentence with static and \\ non-static channels} (2.4cm,-0.5cm) -- (2.4cm, -0.3cm);	
-	%\draw [thick] (3.6cm, -0.3cm) -- (3.6cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{Convolutional layer with \\ multiple filter widths and \\ feature maps} (6cm,-0.5cm) -- (6cm, -0.3cm);
-	%\draw [thick] (7.2cm, -0.3cm) -- (7.2cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{Max-over-time\\  pooling} (9cm,-0.5cm) -- (9cm, -0.3cm);
-	%\draw [thick] (10cm, -0.3cm) -- (10cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{Fully connected layer \\ with dropout and \\ softmax output} (11.7cm,-0.5cm) -- (11.7cm, -0.3cm);
-	\draw [thick] (0cm, -0.3cm) -- (0cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{维度大小为 $m \times K$ \\ 的静态与非静态通道\\的句子表示} (2.4cm,-0.5cm) -- (2.4cm, -0.3cm);	
+
+	\draw [thick] (0cm, -0.3cm) -- (0cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{维度大小为 $m \times O$ \\ 的句子表示} (2.4cm,-0.5cm) -- (2.4cm, -0.3cm);	
 	\draw [thick] (3.6cm, -0.3cm) -- (3.6cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{具有多个不同大小\\的卷积核和特征图\\的卷积层} (6cm,-0.5cm) -- (6cm, -0.3cm);
 	\draw [thick] (7.2cm, -0.3cm) -- (7.2cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{最大池化} (9cm,-0.5cm) -- (9cm, -0.3cm);
 	\draw [thick] (10cm, -0.3cm) -- (10cm, -0.5cm)  -- node[font=\tiny, align=center,yshift=-0.5cm]{带有Dropout\\和Softmax输出\\的全连接层} (11.7cm,-0.5cm) -- (11.7cm, -0.3cm);
 	
 	
-	 %\node [font=\Large] at (5.2cm,-2cm){$h_i = dot(F,x_{i:i+l-1})+b$};
-	
 \end{scope}
 
 \end{tikzpicture}
\ No newline at end of file

Chapter12/Figures/figure-position-of-difference-and-layer-regularization-in-the-model.tex

@@ -16,8 +16,9 @@
 \node [Resnode,anchor=south] (res1) at ([yshift=0.3em]sa1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [ffnnode,anchor=south] (ffn1) at ([yshift=1em]res1.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res2) at ([yshift=0.3em]ffn1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1em]sa1.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1em,xshift=0.5em]sa1.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (inputs) at ([yshift=-3em]sa1.south) {\scriptsize{$\textbf{编码器输入: 我\ \ 很\ \ 好}$}};
 \node [anchor=south] (encoder) at ([xshift=0.2em,yshift=0.6em]res2.north west) {\scriptsize{\textbf{编码器}}};
 
@@ -35,8 +36,9 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=1em]res4.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res5) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [outputnode,anchor=south] (o1) at ([yshift=1em]res5.north) {\tiny{$\textbf{Output layer}$}};
-\node [inputnode,anchor=north west] (input2) at ([yshift=-1em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos2) at ([yshift=-1em]sa2.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input2) at ([yshift=-1em,xshift=-0.5em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa2.south west) {$+$};
+\node [posnode,anchor=north east] (pos2) at ([yshift=-1em,xshift=0.5em]sa2.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (outputs) at ([yshift=-3em]sa2.south) {\scriptsize{$\textbf{解码器输入: $<$sos$>$ I  am  fine}$}};
 \node [anchor=east] (decoder) at ([xshift=-1em,yshift=-1.5em]o1.west) {\scriptsize{\textbf{解码器}}};
 \node [anchor=north] (decoutputs) at ([yshift=1.5em]o1.north) {\scriptsize{$\textbf{解码器输出: I  am  fine $<$eos$>$ }$}};

Chapter12/Figures/figure-position-of-feedforward-neural-network-in-the-model.tex

@@ -14,8 +14,9 @@
 \node [Resnode,anchor=south] (res1) at ([yshift=0.3em]sa1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [ffnnode,anchor=south] (ffn1) at ([yshift=1em]res1.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res2) at ([yshift=0.3em]ffn1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1em]sa1.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1em,xshift=0.5em]sa1.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (inputs) at ([yshift=-3em]sa1.south) {\scriptsize{$\textbf{编码器输入: 我\ \ 很\ \ 好}$}};
 \node [anchor=south] (encoder) at ([xshift=0.2em,yshift=0.6em]res2.north west) {\scriptsize{\textbf{编码器}}};
 
@@ -33,8 +34,9 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=1em]res4.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res5) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [outputnode,anchor=south] (o1) at ([yshift=1em]res5.north) {\tiny{$\textbf{Output layer}$}};
-\node [inputnode,anchor=north west] (input2) at ([yshift=-1em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos2) at ([yshift=-1em]sa2.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input2) at ([yshift=-1em,xshift=-0.5em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa2.south west) {$+$};
+\node [posnode,anchor=north east] (pos2) at ([yshift=-1em,xshift=0.5em]sa2.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (outputs) at ([yshift=-3em]sa2.south) {\scriptsize{$\textbf{解码器输入: $<$sos$>$ I  am  fine}$}};
 \node [anchor=east] (decoder) at ([xshift=-1em,yshift=-1.5em]o1.west) {\scriptsize{\textbf{解码器}}};
 \node [anchor=north] (decoutputs) at ([yshift=1.5em]o1.north) {\scriptsize{$\textbf{解码器输出: I  am  fine $<$eos$>$ }$}};

Chapter12/Figures/figure-position-of-self-attention-mechanism-in-the-model.tex

@@ -15,8 +15,9 @@
 \node [Resnode,anchor=south] (res1) at ([yshift=0.3em]sa1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [ffnnode,anchor=south] (ffn1) at ([yshift=1em]res1.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res2) at ([yshift=0.3em]ffn1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1em]sa1.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1em,xshift=0.5em]sa1.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (inputs) at ([yshift=-3em]sa1.south) {\scriptsize{$\textbf{编码器输入: 我\ \ 很\ \ 好}$}};
 \node [anchor=south] (encoder) at ([xshift=0.2em,yshift=0.6em]res2.north west) {\scriptsize{\textbf{编码器}}};
 
@@ -34,8 +35,9 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=1em]res4.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res5) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [outputnode,anchor=south] (o1) at ([yshift=1em]res5.north) {\tiny{$\textbf{Output layer}$}};
-\node [inputnode,anchor=north west] (input2) at ([yshift=-1em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos2) at ([yshift=-1em]sa2.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input2) at ([yshift=-1em,xshift=-0.5em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa2.south west) {$+$};
+\node [posnode,anchor=north east] (pos2) at ([yshift=-1em,xshift=0.5em]sa2.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (outputs) at ([yshift=-3em]sa2.south) {\scriptsize{$\textbf{解码器输入: $<$sos$>$ I  am  fine}$}};
 \node [anchor=east] (decoder) at ([xshift=-1em,yshift=-1.5em]o1.west) {\scriptsize{\textbf{解码器}}};
 \node [anchor=north] (decoutputs) at ([yshift=1.5em]o1.north) {\scriptsize{$\textbf{解码器输出: I  am  fine $<$eos$>$ }$}};

Chapter12/Figures/figure-transformer-input-and-position-encoding.tex

@@ -14,8 +14,9 @@
 \node [Resnode,anchor=south] (res1) at ([yshift=0.3em]sa1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [ffnnode,anchor=south] (ffn1) at ([yshift=1em]res1.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res2) at ([yshift=0.3em]ffn1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1em]sa1.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1em,xshift=0.5em]sa1.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (inputs) at ([yshift=-3em]sa1.south) {\scriptsize{$\textbf{编码器输入: 我\ \ 很\ \ 好}$}};
 \node [anchor=south] (encoder) at ([xshift=0.2em,yshift=0.6em]res2.north west) {\scriptsize{\textbf{编码器}}};
 
@@ -33,8 +34,9 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=1em]res4.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res5) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [outputnode,anchor=south] (o1) at ([yshift=1em]res5.north) {\tiny{$\textbf{Output layer}$}};
-\node [inputnode,anchor=north west] (input2) at ([yshift=-1em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos2) at ([yshift=-1em]sa2.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input2) at ([yshift=-1em,xshift=-0.5em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa2.south west) {$+$};
+\node [posnode,anchor=north east] (pos2) at ([yshift=-1em,xshift=0.5em]sa2.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (outputs) at ([yshift=-3em]sa2.south) {\scriptsize{$\textbf{解码器输入: $<$sos$>$ I  am  fine}$}};
 \node [anchor=east] (decoder) at ([xshift=-1em,yshift=-1.5em]o1.west) {\scriptsize{\textbf{解码器}}};
 \node [anchor=north] (decoutputs) at ([yshift=1.5em]o1.north) {\scriptsize{$\textbf{解码器输出: I  am  fine $<$eos$>$ }$}};

Chapter12/Figures/figure-transformer.tex

@@ -14,8 +14,9 @@
 \node [Resnode,anchor=south] (res1) at ([yshift=0.3em]sa1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [ffnnode,anchor=south] (ffn1) at ([yshift=1em]res1.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res2) at ([yshift=0.3em]ffn1.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1em]sa1.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1em,xshift=0.5em]sa1.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (inputs) at ([yshift=-3em]sa1.south) {\scriptsize{$\textbf{编码器输入: 我\ \ 很\ \ 好}$}};
 \node [anchor=south] (encoder) at ([xshift=0.2em,yshift=0.6em]res2.north west) {\scriptsize{\textbf{编码器}}};
 
@@ -33,8 +34,9 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=1em]res4.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res5) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 \node [outputnode,anchor=south] (o1) at ([yshift=1em]res5.north) {\tiny{$\textbf{Output layer}$}};
-\node [inputnode,anchor=north west] (input2) at ([yshift=-1em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
-\node [posnode,anchor=north east] (pos2) at ([yshift=-1em]sa2.south east) {\tiny{$\textbf{Position}$}};
+\node [inputnode,anchor=north west] (input2) at ([yshift=-1em,xshift=-0.5em]sa2.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-1.6em,xshift=3.5em]sa2.south west) {$+$};
+\node [posnode,anchor=north east] (pos2) at ([yshift=-1em,xshift=0.5em]sa2.south east) {\tiny{$\textbf{Position}$}};
 \node [anchor=north] (outputs) at ([yshift=-3em]sa2.south) {\scriptsize{$\textbf{解码器输入: $<$sos$>$ I  am  fine}$}};
 \node [anchor=east] (decoder) at ([xshift=-1em,yshift=-1.5em]o1.west) {\scriptsize{\textbf{解码器}}};
 \node [anchor=north] (decoutputs) at ([yshift=1.5em]o1.north) {\scriptsize{$\textbf{解码器输出: I  am  fine $<$eos$>$ }$}};

Chapter12/chapter12.tex

@@ -123,7 +123,7 @@
 %----------------------------------------------
 \begin{table}[htp]
 \centering
-\caption{ 不同翻译模型性能对比\upcite{NIPS2017_7181}}
+\caption{ 不同翻译模型性能对比\upcite{vaswani2017attention}}
 \label{tab:12-12}
 \begin{tabular}{l l l l}
 \multicolumn{1}{l|}{\multirow{2}{*}{系统}} & \multicolumn{2}{c}{BLEU[\%]} & \multirow{2}{*}{\parbox{6em}{模型训练代价 (FLOPs)}} \\
@@ -324,11 +324,11 @@
 
 \begin{itemize}
 \vspace{0.5em}
-\item 首先，将$\mathbi{Q}$、$\mathbi{K}$、$\mathbi{V}$分别通过线性（Linear）变换的方式映射为$h$个子集。即$\mathbi{Q}_i = \mathbi{Q}\mathbi{W}_i^Q $、$\mathbi{K}_i = \mathbi{K}\mathbi{W}_i^K $、$\mathbi{V}_i = \mathbi{V}\mathbi{W}_i^V $，其中$i$表示第$i$个头， $\mathbi{W}_i^Q  \in \mathbb{R}^{d_{model} \times d_k}$,  $\mathbi{W}_i^K  \in \mathbb{R}^{d_{model} \times d_k}$,  $\mathbi{W}_i^V  \in \mathbb{R}^{d_{model} \times d_v}$是参数矩阵; $d_k=d_v=d_{model} / h$，对于不同的头采用不同的变换矩阵，这里$d_{model}$表示每个隐层向量的维度；
+\item 首先，将$\mathbi{Q}$、$\mathbi{K}$、$\mathbi{V}$分别通过线性（Linear）变换的方式映射为$h$个子集。即$\mathbi{Q}_i = \mathbi{Q}\mathbi{W}_i^{\,Q} $、$\mathbi{K}_i = \mathbi{K}\mathbi{W}_i^{\,K} $、$\mathbi{V}_i = \mathbi{V}\mathbi{W}_i^{\,V} $，其中$i$表示第$i$个头， $\mathbi{W}_i^{\,Q}  \in \mathbb{R}^{d_{model} \times d_k}$,  $\mathbi{W}_i^{\,K}  \in \mathbb{R}^{d_{model} \times d_k}$,  $\mathbi{W}_i^{\,V}  \in \mathbb{R}^{d_{model} \times d_v}$是参数矩阵; $d_k=d_v=d_{model} / h$，对于不同的头采用不同的变换矩阵，这里$d_{model}$表示每个隐层向量的维度；
 \vspace{0.5em}
 \item 其次，对每个头分别执行点乘注意力操作，并得到每个头的注意力操作的输出$\mathbi{head}_i$；
 \vspace{0.5em}
-\item 最后，将$h$个头的注意力输出在最后一维$d_v$进行拼接（Concat）重新得到维度为$h \times d_v$的输出，并通过对其左乘一个权重矩阵$\mathbi{W}^o$进行线性变换，从而对多头计算得到的信息进行融合，且将多头注意力输出的维度映射为模型的隐层大小（即$d_{model}$），这里参数矩阵$\mathbi{W}^o \in \mathbb{R}^{h \times d_v \times d_{model}}$。
+\item 最后，将$h$个头的注意力输出在最后一维$d_v$进行拼接（Concat）重新得到维度为$h \times d_v$的输出，并通过对其左乘一个权重矩阵$\mathbi{W}^{\,o}$进行线性变换，从而对多头计算得到的信息进行融合，且将多头注意力输出的维度映射为模型的隐层大小（即$d_{model}$），这里参数矩阵$\mathbi{W}^{\,o} \in \mathbb{R}^{h d_v \times d_{model}}$。
 \vspace{0.5em}
 \end{itemize}
 
@@ -343,8 +343,8 @@
 
 \parinterval 多头机制可以被形式化描述为如下公式：
 \begin{eqnarray}
-\textrm{MultiHead}(\mathbi{Q}, \mathbi{K} , \mathbi{V})& = & \textrm{Concat} (\mathbi{head}_1, ... , \mathbi{head}_h ) \mathbi{W}^o \label{eq:12-48} \\
-\mathbi{head}_i & = &\textrm{Attention} (\mathbi{Q}\mathbi{W}_i^Q , \mathbi{K}\mathbi{W}_i^K  , \mathbi{V}\mathbi{W}_i^V )
+\textrm{MultiHead}(\mathbi{Q}, \mathbi{K} , \mathbi{V})& = & \textrm{Concat} (\mathbi{head}_1, ... , \mathbi{head}_h ) \mathbi{W}^{\,o} \label{eq:12-48} \\
+\mathbi{head}_i & = &\textrm{Attention} (\mathbi{Q}\mathbi{W}_i^{\,Q} , \mathbi{K}\mathbi{W}_i^{\,K}  , \mathbi{V}\mathbi{W}_i^{\,V} )
 \label{eq:12-49}
 \end{eqnarray}
 
@@ -383,7 +383,7 @@
 
 \section{残差网络和层正则化}
 
-\parinterval Transformer编码器、解码器分别由多层网络组成（通常为6层），每层网络又包含多个子层（自注意力网络、前馈神经网络）。因此Transformer实际上是一个很深的网络结构。再加上点乘注意力机制中包含很多线性和非线性变换；且注意力函数Attention($\cdot$)的计算也涉及多层网络，整个网络的信息传递非常复杂。从反向传播的角度来看，每次回传的梯度都会经过若干步骤，容易产生梯度爆炸或者消失。解决这个问题的一种办法就是使用残差连接\upcite{DBLP:journals/corr/HeZRS15}，此部分内容已经在{\chaptereleven}进行了介绍，这里不再赘述。
+\parinterval Transformer编码器、解码器分别由多层网络组成（通常为6层），每层网络又包含多个子层（自注意力网络、前馈神经网络）。因此Transformer实际上是一个很深的网络结构。再加上点乘注意力机制中包含很多线性和非线性变换；且注意力函数Attention($\cdot$)的计算也涉及多层网络，整个网络的信息传递非常复杂。从反向传播的角度来看，每次回传的梯度都会经过若干步骤，容易产生梯度爆炸或者消失。解决这个问题的一种办法就是使用残差连接\upcite{DBLP:journals/corr/HeZRS15}，此部分内容已经在{\chapternine}进行了介绍，这里不再赘述。
 
 %\parinterval 解决这个问题的一种办法就是使用残差连接\upcite{DBLP:journals/corr/HeZRS15}。残差连接是一种用来训练深层网络的技术，其结构如图\ref{fig:12-49}，即在子层之前通过增加直接连接的方式，将底层信息直接传递给上层。
 
@@ -416,13 +416,13 @@
 \parinterval 在Transformer的训练过程中，由于引入了残差操作，将前面所有层的输出加到一起，如公式：
 \begin{eqnarray}
 %x_{l+1} = x_l + F (x_l)
-\mathbi{h}^{l+1} = F (\mathbi{h}^l) + \mathbi{h}^l
+\mathbi{x}^{l+1} = F (\mathbi{x}^l) + \mathbi{x}^l
 \label{eq:12-50}
 \end{eqnarray}
 
-\noindent 其中$\mathbi{h}^l$表示第$l$层网络的输入向量，$F (\mathbi{h}^l)$是子层运算，这样会导致不同层（或子层）的结果之间的差异性很大，造成训练过程不稳定、训练时间较长。为了避免这种情况，在每层中加入了层正则化操作\upcite{Ba2016LayerN}。图\ref{fig:12-50} 中的红色方框展示了Transformer中残差和层正则化的位置。层正则化的计算公式如下：
+\noindent 其中$\mathbi{x}^l$表示第$l$层网络的输入向量，$F (\mathbi{x}^l)$是子层运算，这样会导致不同层（或子层）的结果之间的差异性很大，造成训练过程不稳定、训练时间较长。为了避免这种情况，在每层中加入了层正则化操作\upcite{Ba2016LayerN}。图\ref{fig:12-50} 中的红色方框展示了Transformer中残差和层正则化的位置。层正则化的计算公式如下：
 \begin{eqnarray}
-\textrm{LN}(\mathbi{h}) = g \cdot \frac{\mathbi{h}- \mu} {\sigma} + b
+\textrm{LN}(\mathbi{x}) = g \cdot \frac{\mathbi{x}- \mu} {\sigma} + b
 \label{eq:12-51}
 \end{eqnarray}
 
@@ -527,7 +527,7 @@ lrate = d_{\textrm{model}}^{-0.5} \cdot \textrm{min} (\textrm{step}^{-0.5} , \te
 \vspace{0.5em}
 \end{itemize}
 
-\parinterval 不同的Transformer可以适应不同的任务，常见的Transformer模型有Transformer Base、Transformer Big和Transformer Deep\upcite{NIPS2017_7181,WangLearning}，具体设置如下：
+\parinterval 不同的Transformer可以适应不同的任务，常见的Transformer模型有Transformer Base、Transformer Big和Transformer Deep\upcite{vaswani2017attention,WangLearning}，具体设置如下：
 
 \begin{itemize}
 \vspace{0.5em}

bibliography.bib

@@ -4,11 +4,12 @@
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 %%%%% chapter 1------------------------------------------------------
 
-@book{慧立彦宗1983大慈恩寺三藏法师传,
-  title={大慈恩寺三藏法师传},
-  author={慧立彦宗},
-  publisher={中华书局},
-  year={1983},
+@book{慧立2000大慈恩寺三藏法師傳,
+  title={大慈恩寺三藏法師傳},
+  author={慧立 and 彦悰 and 道宣},
+  volume={2},
+  year={2000},
+  publisher={中华书局}
 }
 
 @book{2019cns,
@@ -5219,7 +5220,7 @@ author    = {Yoshua Bengio and
 
 @article{Waibel1989PhonemeRU,
   title={Phoneme recognition using time-delay neural networks},
-  author={Alexander Waibel and Toshiyuki Hanazawa and Geoffrey Hinton and Kiyohiro Shikano and K.J. Lang},
+  author={Alexander Waibel and Toshiyuki Hanazawa and Geoffrey Everest Hinton and Kiyohiro Shikano and K.J. Lang},
   journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
   year={1989},
   volume={37},
@@ -5228,7 +5229,7 @@ author    = {Yoshua Bengio and
 
 @article{LeCun1989BackpropagationAT,
   title={Backpropagation Applied to Handwritten Zip Code Recognition},
-  author={Yann LeCun and Bernhard Boser and John Denker and Don Henderson and R. Howard and W.E. Hubbard and Larry Jackel},
+  author={Yann LeCun and Bernhard Boser and John Denker and Don Henderson and R.E.Howard and W.E. Hubbard and Larry Jackel},
   journal={Neural Computation},
   year={1989},
   volume={1},
@@ -5236,7 +5237,7 @@ author    = {Yoshua Bengio and
 }
 
 @article{726791,
-  author={Yann {Lecun} and Leon {Bottou} and Y. {Bengio} and Patrick {Haffner}},
+  author={Yann {Lecun} and Leon {Bottou} and Yoshua {Bengio} and Patrick {Haffner}},
   journal={Proceedings of the IEEE}, 
   title={Gradient-based learning applied to document recognition}, 
   year={1998},
@@ -5448,7 +5449,7 @@ author    = {Yoshua Bengio and
 @inproceedings{Islam2020HowMP,
   author    = {Md. Amirul Islam and
                Sen Jia and
-               Neil D. B. Bruce},
+               Neil Bruce},
   title     = {How much Position Information Do Convolutional Neural Networks Encode?},
   publisher = {International Conference on Learning Representations},
   year      = {2020},
@@ -5458,7 +5459,7 @@ author    = {Yoshua Bengio and
   author    = {Ilya Sutskever and
                James Martens and
                George E. Dahl and
-               Geoffrey E. Hinton},
+               Geoffrey Everest Hinton},
   publisher = {International Conference on Machine Learning},
   pages     = {1139--1147},
   year={2013}
@@ -5473,7 +5474,7 @@ author    = {Yoshua Bengio and
 }
 
 @article{JMLR:v15:srivastava14a,
-  author  = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
+  author  = {Nitish Srivastava and Geoffrey Everest Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
   title   = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
   journal = {Journal of Machine Learning Research},
   year    = {2014},
@@ -5491,7 +5492,7 @@ author    = {Yoshua Bengio and
 
 @article{Howard2017MobileNetsEC,
   title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
-  author    = {Andrew G. Howard and
+  author    = {Andrew Howard and
                Menglong Zhu and
                Bo Chen and
                Dmitry Kalenichenko and
@@ -5522,7 +5523,7 @@ author    = {Yoshua Bengio and
   title={Locally-connected and convolutional neural networks for small footprint speaker recognition},
   author    = {Yu-hsin Chen and
                Ignacio Lopez-Moreno and
-               Tara N. Sainath and
+               Tara Sainath and
                Mirk{\'{o}} Visontai and
                Raziel Alvarez and
                Carolina Parada},