up

AAAI2021/paper.tex

@@ -177,11 +177,7 @@
   inductions. 
   
   In this paper, we are the first to successfully achieve high compositional symbolic
-<<<<<<< HEAD
   language in a \emph{natural} manner without handcrafted inductions.
-=======
-  language in a \emph{natural} manner.
->>>>>>> 65d6269911adf7729e1964b9c3faa0211fce0f3b
   Initially, by thoroughly investigating the compositionality of emerged symbolic
   language after removing the \emph{deliberately handcrafted}
   inductions, we observe that the agent capacity plays a key role in

AAAI2021/tex/introduction.tex

@@ -37,7 +37,7 @@ More recently, measuring the compositionality \note{xxxxx}.}
   \centering
   \includegraphics[width=0.9\columnwidth]{fig/occupy}
   \caption{\rmk{compositionality.}}
-  \label{fig:symbols}
+  \label{fig:induction}
   \end{figure}
 
 Prior studies focus on achieving high compositional symbolic language 
@@ -45,10 +45,10 @@ through \emph{deliberately handcrafted} inductions, e.g., small vocabulary
 sizes~\cite{}, memoryless~\cite{}, carefully constructed rewards~\cite{}, and
 ease-of-teaching~\cite{}. \note{The basic intuition is that high compositional symbolic
 language cannot emerge without induction in existing multi-agent environment.}
-Figure~\ref{fig:xx} reports the compositionality when training two agents in the widely-used
+Figure~\ref{fig:induction} reports the compositionality when training two agents in the widely-used
 listener-speaker referential game, and it can be observed that \note{the compositionality
 of emerged symbolic language is extremely low}.
-Though such unnatural inductions are crucial, they prevent us from better understanding the mystery of
+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
 \emph{naturally}, i.e., without handcrafted inductions.