Add NMT vs. SMT/Human tables

Section06-Neural-Machine-Translation/section06.tex

@@ -21,6 +21,7 @@
 \usepackage{tikz-3dplot}
 \usepackage{esvect}
 \usepackage{CJKulem}
+\usepackage{booktabs}
 
 \usepackage{tcolorbox}
 \tcbuselibrary{skins}
@@ -190,7 +191,47 @@
 \begin{frame}{神经机器翻译的进展(续)}
 \begin{itemize}
 \item 性能提升
+\only<1>{
+    \begin{center}
+        \begin{tabular}{r}
+            \begin{tabular}{lcccl}
+                \toprule
+                \multirow{2}{*}{\#} & \multicolumn{3}{c}{自动评价} & \multirow{2}{*}{系统} \\
+                \cline{2-4}
+                & \footnotesize BLEU & \footnotesize HTER & \footnotesize mTER & \\
+                \midrule
+                统计机器翻译 & 25.3 & 28.0 & 21.8 & PBSY \\
+                & 24.6 & 29.9 & 23.4 & HPB \\
+                & 25.8 & 29.0 & 22.7 & SPB \\
+                \midrule
+                神经机器翻译 & \textbf{31.1} & \textbf{21.1} & \textbf{16.2} & NMT \\
+                \bottomrule
+            \end{tabular}\\[4pt]
+            \tiny *Neural versus Phrase-Based Machine Translation Quality: a Case Study\\
+        \end{tabular}
+    \end{center}
+}
 \item Human party MT
+\only<2>{
+    \begin{center}
+        \begin{tabular}{r}
+            \begin{tabular}{lrl}
+                \toprule
+                \# & 人工评价 & 系统 \\
+                \midrule
+                机器翻译 & \textbf{69.9} & COMBO-6 \\
+                & 69.8 & COMBO-4 \\
+                & \textbf{69.9} & COMBO-5 \\
+                \midrule
+                人工翻译 & 68.6 & REFERENCE-HT \\
+                & 67.6 & REFERENCE-PE \\
+                & 62.1 & REFERENCE-WMT \\
+                \bottomrule
+            \end{tabular}\\[4pt]
+            \tiny *Achieving Human Parity on Automatic Chinese to English News Translation\\
+        \end{tabular}
+    \end{center}
+}
 \end{itemize}
 %%% 进一步找一些证据说明NMT的进展，很大google、microsoft的文章，可以看看提升了多少性能等等
 \end{frame}