Merge branch 'master' of http://62.234.201.16/hao/AAAI21_Emergent_language

AAAI2021/tex/relatedwork.tex

@@ -14,7 +14,7 @@ the real world. None of these works realizes the importance of model capacity of
 agent itself. \rmk{this should be largely emphasized.}
 
 
-\begin{table}[b]
+\begin{table*}[htbp]
   \centering
   \small
   \caption{Handcrafted inductions in related works.}
@@ -23,12 +23,17 @@ agent itself. \rmk{this should be largely emphasized.}
     \toprule
     Works & Handcrafted induction & Compositionality\\ 
     \midrule
-    &&\\
-    &&\\
-    \textbf{Ours} & \textbf{None} & \textbf{High} \\
+    \cite{kirby2015compression}&Expressivity and compressibility&Qualitative, Speaker\\
+    \cite{kottur-etal-2017-natural}&Vocabulary size, listener's memory&Qualitative, Speaker\\
+    \cite{choi2018compositional}&Vocabulary size, maximum message length&Qualitative, Speaker+Listener\\
+    \cite{lazaridou2018emergence}&Structure of input data&Quantitative, Speaker\\
+    \cite{evtimova2018emergent}&Multi-modal scenarios&Quantitative, Speaker\\
+    \cite{li2019ease}&Population size, resetting all listeners&Quantitative, Speaker\\
+    \cite{chaabouni2020compositionality}&Easier to decode&Quantitative, Speaker\\
+    \textbf{Ours} & \textbf{None} & \textbf{Quantitative, Speaker+Listener} \\
     \bottomrule
     \end{tabular}
-  \end{table}
+  \end{table*}
 
 %measure
 To measure the compositionality of emerged symbolic language, many metrics are