~

AAAI2021/paper.tex

-\documentclass[letterpaper]{article} % DO NOT CHANGE THIS
+ \documentclass[letterpaper]{article} % DO NOT CHANGE THIS
 \def\year{2021}\relax
 %File: formatting-instructions-latex-2021.tex
 %release 2021.1
@@ -178,7 +178,7 @@
  The emergence of symbolic languages with high compositionality has
   attracted extensive attention from a broad range of communities. Existing
   studies achieve high compositionality through \emph{deliberately handcrafted}
-  inductions (e.g., small vocabulary sizes, addtional rewards, constructed 
+  inductions (e.g., addtional rewards, constructed 
   loss functions and ease-of-teaching) in multi-agent learning, which are unnatural. 
   Yet, few studies investigate the emergence of symbolic language with high
   compositionality \emph{naturally}, i.e., without deliberately handcrafted

AAAI2021/tex/experiments.tex

@@ -43,7 +43,7 @@ Figure~\ref{fig:exp2} (a) and (b) for $MIS>0.99$ and $MIS>0.9$, respectively. It
 can be observed that the ratio of high compositional symbolic languages
 decreases drastically with the increase of $h_{size}$.
 Taking vocabulary size $|V|=4$ as an example, symbolic languages with
-compositionality $MIS>0.99$ take only around 10\% over all the emerged symbolic
+compositionality $MIS>0.99$ take $>$10\% mainly over all the emerged symbolic
 languages, when $h_{size}<20$; the ratio reduces to 0\%$\sim$5\% when $h_{size}$
 increases to 40; the ratio reduces around 3\% when $h_{size}$ goes beyond 40. 
 $MIS>0.9$ reports similar results.

AAAI2021/tex/introduction.tex

@@ -39,10 +39,12 @@ vocabulary can express almost infinite concepts.}
 %
 \begin{figure}[t]
   \centering
-  \includegraphics[width=0.99\columnwidth]{fig/Figure1_motivation.pdf}
-  \caption{The distribution of compositionality when training 50 times without
+  \includegraphics[width=0.99\columnwidth]{fig/Figure1-motivation.pdf}
+  \caption{The distribution of compositionality when training for 100 symbolic
+    languages without
     any induction. It can be observed that high compositional symbolic language
-    seldom emerged (e.g., 0 for compositionality $>0.99$).}
+    seldom emerged (e.g., $<5\%$ for compositionality $>0.99$). Moreover, varying
+    the vocabulary size does not affect the compositionality notably.}
   \label{fig:induction}
   \end{figure}
 
@@ -52,8 +54,10 @@ sizes~\cite{}, memoryless~\cite{}, addtional rewards~\cite{}, constructed loss f
 ease-of-teaching~\cite{}. \note{The possible intuition is that high compositional symbolic
 language cannot emerge without induction in existing multi-agent environment.}
 Figure~\ref{fig:induction} reports the compositionality when training two agents
-in the widely-used listener-speaker referential game for 50 times, and it can be observed that \note{the compositionality
-of emerged symbolic language is extremely low without any induction}.
+in the widely-used listener-speaker referential game for emerging 100 symbolic
+languages, and it can be observed that \note{the compositionality
+of emerged symbolic language is extremely low without any induction. Moreover, varying
+    the vocabulary size does not affect the compositionality notably.}
 Though such unnatural inductions are useful, they prevent us from better understanding the mystery of
 the emergence of language and even intelligence among our pre-human ancestors.
 Yet, few works investigate the emergence of high compositional symbolic language