udpates of section 7

Book/Chapter7/Figures/figure-norm.tex

@@ -18,7 +18,7 @@
 	\node[] (res1) at ([xshift=2.4em]fn1.east) {+};
 
 	\node[anchor=west,inputnode] (output) at ([xshift=1.2em]res1.east) {$x_{i}^{l+1}$};
-	\node[anchor=west,inputnode] (legend1) at (8em,-1em) {(a) 标准Transformer网络};
+	\node[anchor=west,inputnode] (legend1) at (6em,-1em) {(a) 标准Transformer网络};
 
 	%\coordinate (mend) at ([xshift=1em]m.west);
 	\draw[-latex',thick] (input)--(ln);
@@ -38,7 +38,7 @@
 	\draw[-latex',thick,rounded corners] (h1) -- ([yshift=1.35em]h1.north) -- ([yshift=1em]m1.north) -- (m1.north);
 	%--------------------------------------------------------
 	
-	\node[anchor=south west,inputnode] (input_2) at (0,-4em) {$x_{i}^{l}$};
+	\node[anchor=south west,inputnode] (input_2) at (0,-6em) {$x_{i}^{l}$};
 	
 	\node[anchor=west,sublayernode,fill=red!10] (ln_2) at ([xshift=1.2em]input_2.east) {LN};
 	\node[anchor=west,sublayernode,fill=green!10] (fn_2) at ([xshift=1.2em]ln_2.east) {F};
@@ -51,7 +51,7 @@
 	\node[] (res1_2) at ([xshift=2.4em]fn1_2.east) {+};
 	
 	\node[anchor=west,inputnode] (output_2) at ([xshift=1.2em]res1_2.east) {$x_{i}^{l+1}$};
-	\node[anchor=west,inputnode] (legend2) at (6.5em,-5.5em) {(b) 引入Layer Dropout后的Transformer网络};
+	\node[anchor=west,inputnode] (legend2) at (2.5em,-7.5em) {(b) 引入Layer Dropout后的Transformer网络};
 
 	\node[anchor=south west,inputnode,red,font=\tiny] (mlable) at ([xshift=-2.2em,yshift=-0.6em]m_2.south) {M=1};
 

Book/mt-book-xelatex.idx

@@ -31,31 +31,32 @@
 \indexentry{Denoising|hyperpage}{21}
 \indexentry{泛化|hyperpage}{21}
 \indexentry{Generalization|hyperpage}{21}
+\indexentry{标签平滑|hyperpage}{23}
+\indexentry{Label Smoothing|hyperpage}{23}
 \indexentry{相互适应|hyperpage}{24}
 \indexentry{Co-Adaptation|hyperpage}{24}
 \indexentry{集成学习|hyperpage}{25}
 \indexentry{Ensemble Learning|hyperpage}{25}
 \indexentry{容量|hyperpage}{26}
 \indexentry{Capacity|hyperpage}{26}
-\indexentry{宽残差网络|hyperpage}{26}
-\indexentry{Wide Residual Network|hyperpage}{26}
+\indexentry{宽残差网络|hyperpage}{27}
+\indexentry{Wide Residual Network|hyperpage}{27}
 \indexentry{探测任务|hyperpage}{28}
 \indexentry{Probing Task|hyperpage}{28}
-\indexentry{浅层网络表示|hyperpage}{28}
 \indexentry{表面信息|hyperpage}{28}
 \indexentry{Surface Information|hyperpage}{28}
-\indexentry{中间层的表示|hyperpage}{28}
 \indexentry{语法信息|hyperpage}{28}
 \indexentry{Syntactic Information|hyperpage}{28}
-\indexentry{顶层网络的表示|hyperpage}{28}
 \indexentry{语义信息|hyperpage}{28}
 \indexentry{Semantic Information|hyperpage}{28}
-\indexentry{词嵌入|hyperpage}{28}
-\indexentry{Embedding|hyperpage}{28}
+\indexentry{词嵌入|hyperpage}{29}
+\indexentry{Embedding|hyperpage}{29}
 \indexentry{数据并行|hyperpage}{29}
 \indexentry{Data Parallelism|hyperpage}{29}
 \indexentry{模型并行|hyperpage}{29}
 \indexentry{Model Parallelism|hyperpage}{29}
+\indexentry{小批量训练|hyperpage}{29}
+\indexentry{Mini-batch Training|hyperpage}{29}
 \indexentry{课程学习|hyperpage}{31}
 \indexentry{Curriculum Learning|hyperpage}{31}
 \indexentry{推断|hyperpage}{32}
@@ -66,6 +67,10 @@
 \indexentry{Search Error|hyperpage}{32}
 \indexentry{模型错误|hyperpage}{32}
 \indexentry{Modeling Error|hyperpage}{32}
+\indexentry{重排序|hyperpage}{34}
+\indexentry{Re-ranking|hyperpage}{34}
+\indexentry{双向推断|hyperpage}{34}
+\indexentry{Bidirectional Inference|hyperpage}{34}
 \indexentry{批量推断|hyperpage}{37}
 \indexentry{Batch Inference|hyperpage}{37}
 \indexentry{批量处理|hyperpage}{37}
@@ -92,10 +97,10 @@
 \indexentry{Diversity|hyperpage}{45}
 \indexentry{重排序|hyperpage}{45}
 \indexentry{Re-ranking|hyperpage}{45}
-\indexentry{动态线性层聚合方法|hyperpage}{50}
-\indexentry{Dynamic Linear Combination of Layers，DLCL|hyperpage}{50}
-\indexentry{相互适应|hyperpage}{54}
-\indexentry{Co-adaptation|hyperpage}{54}
+\indexentry{动态线性层聚合方法|hyperpage}{51}
+\indexentry{Dynamic Linear Combination of Layers，DLCL|hyperpage}{51}
+\indexentry{相互适应|hyperpage}{55}
+\indexentry{Co-adaptation|hyperpage}{55}
 \indexentry{数据增强|hyperpage}{57}
 \indexentry{Data Augmentation|hyperpage}{57}
 \indexentry{回译|hyperpage}{57}
@@ -111,7 +116,7 @@
 \indexentry{多任务学习|hyperpage}{60}
 \indexentry{Multitask Learning|hyperpage}{60}
 \indexentry{模型压缩|hyperpage}{61}
-\indexentry{Model Compression|hyperpage}{61}
+\indexentry{Model Compression|hyperpage}{62}
 \indexentry{学习难度|hyperpage}{62}
 \indexentry{Learning Difficulty|hyperpage}{62}
 \indexentry{教师模型|hyperpage}{62}

Book/structure.tex

@@ -2,19 +2,20 @@
 % !TEX encoding = UTF-8 Unicode
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% This file was modified on top of 
 % The Legrand Orange Book
 % Structural Definitions File
-% Version 2.1 (26/09/2018)
 %
 % Original author:
 % Mathias Legrand (legrand.mathias@gmail.com) with modifications by:
 % Vel (vel@latextemplates.com)
 %
-% This file was downloaded from:
-% http://www.LaTeXTemplates.com
+% Current Version is maintained by 
+% Tong Xiao (xiaotong@mail.neu.edu.cn)
+% Runzhe Cao (854581319@qq.com)
 %
-% License:
-% CC BY-NC-SA 3.0 (http://creativecommons.org/licenses/by-nc-sa/3.0/)
+% License of This File:
+% CC BY-NC-SA 4.0 (http://creativecommons.org/licenses/by-nc-sa/4.0/)
 %
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%