~

AAAI2021/tex/introduction.tex

@@ -23,7 +23,7 @@ constituent components and the rule combining them~\cite{}.
 meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is'').
 Compositionality is considered to be a source of the productivity,
 systematicity, and learnability of language, and the reason why a language with finite
-vocabulary can express infinite concepts.}
+vocabulary can express almost infinite concepts.}
 %More recently, measuring the compositionality \note{xxxxx}.}
 
 
@@ -48,7 +48,7 @@ vocabulary can express infinite concepts.}
 
 Prior studies focus on achieving high compositional symbolic language 
 through \emph{deliberately handcrafted} inductions, e.g., small vocabulary
-sizes~\cite{}, memoryless~\cite{}, carefully constructed rewards~\cite{}, and
+sizes~\cite{}, memoryless~\cite{}, addtional rewards~\cite{}, constructed loss functions~\cite{}, and
 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
@@ -182,6 +182,7 @@ In this paper, we made the following contributions:
 \item To our best knowledge, we are the first work to successfully achieve 
 high compositional symbolic
   language naturally, without any deliberately handcrafted induction.
+<<<<<<< HEAD
 \item We analyze the compositionality of emerged symbolic language
   after removing deliberately handcrafted inductions.
 \item We propose a novel mutual information-based metric to measure the
@@ -191,6 +192,15 @@ high compositional symbolic
   experimental results lead to a counter-intuitive conclusion that lower agent
   capacity facilitates the emergence of symbolic language with higher
   compositionality.
+=======
+\item We thoroughly analyze the compositionality of emerged symbolic language
+  after removing deliberately handcrafted inductions, and confirm that the agent
+  capacity acts as a key factor for compositionality.
+\item We experimentally verify the relationship between agent capacity and compositionality
+of symbolic language. Both theoretical analysis and experimental results 
+lead to a counter-intuitive conclusion that lower agent capacity 
+facilitates the emergence of symbolic language with higher compositionality.
+>>>>>>> ea172193997fc5aa562d410ba8d7dfa90276246d
 \end{itemize}
 
 

AAAI2021/tex/relatedwork.tex

@@ -4,7 +4,7 @@
 %external environmental factors
 Previous works focus on the external environmental factors that impact the
 compositionality of emerged symbolic language. 
-For example, ~\citet{kirby2015compression} explored how the pressures for compressivity and compressibility lead the structured language.
+For example, ~\citet{kirby2015compression} explored how the pressures for expressivity and compressibility lead the structured language.
 ~\citet{kottur-etal-2017-natural} constrained the vocabulary size and whether the listener has memory to coax the compositionality of the emergent language.
 ~\citet{lazaridou2018emergence} showed that the degree of structure found in the input data affects the emergence of the symbolic language.
 ~\citet{li2019ease} studied how the pressure, ease of teaching, impact on the iterative language of the population regime.