添加引用

AAAI2021/tex/introduction.tex

@@ -3,11 +3,11 @@
 
 The emergence of language has always been an important issue,
 which attracts attention from a broad range of communities,
-including philology~\cite{}, biology~\cite{}, and computer
+including philology~\cite{partee2008compositionality}, biology~\cite{}, and computer
 science~\cite{}. Especially in computer science, efforts in recent years trying to explore
 the emergent language in virtual multi-agent environments, where
 agents are trained to communicate with neural-network-based methods such as deep
-reinforcement learning~\cite{}.
+reinforcement learning~\cite{kottur-etal-2017-natural,bogin2018emergence,lazaridou2018emergence,choi2018compositional,jaques2019social,mul2019mastering,kharitonov2019egg,labash2020perspective,chaabouni2020compositionality}.
 %Such works can be roughly classified into two categories,
 %referential game~\cite{} and multi-agent reinforcement learning (MARL)~\cite{}, based on
 %the environment setting.  
@@ -18,7 +18,7 @@ The quality of emergent language is typically measured by its
 Compositionality is a principle that determines
 whether the meaning of a complex expression (e.g, phrase), which is assembled out of a
 given set of simple components (e.g., symbols), can be determined by its
-constituent components and the rule combining them~\cite{}.
+constituent components and the rule combining them~\cite{andreas2018measuring,chaabouni2020compositionality}.
 \note{For example, the expression ``AAAI is a conference'' consists of two
 meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is'').
 Compositionality is considered to be a source of productivity,
@@ -40,9 +40,9 @@ vocabulary can express almost infinite concepts.}
 \begin{figure}[t]
   \centering
   \includegraphics[width=\columnwidth]{fig/Figure1_motivation.pdf}
-  \caption{The distribution of compositionality for 100 emergent
+  \caption{The distribution of compositionality for 100 emerged symbolic
     languages without
-    any induction. It can be observed that high compositional language
+    any induction. It can be observed that high compositional symbolic language
     seldom emerged (e.g., $<5\%$ for compositionality $>0.99$). Moreover, varying
     the vocabulary size does not affect the compositionality notably.}
   \label{fig:induction}
@@ -71,11 +71,11 @@ vocabulary can express almost infinite concepts.}
     \end{tabular}
   \end{table*}
 
-Prior studies focus on achieving high compositional language
+Prior studies focus on achieving high compositional symbolic language
 through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{},
-constructed loss functions~\cite{}, structural input data~\cite{},
-memoryless~\cite{}, and ease-of-teaching~\cite{}.
-\note{Such optimization methodologies are driven by the challenges to generate high compositional language without induction in an existing multi-agent environment.}
+constructed loss functions~\cite{kharitonov2019egg}, structural input data~\cite{lazaridou2018emergence,evtimova2018emergent},
+memoryless~\cite{kottur-etal-2017-natural,li2019ease}, and ease-of-teaching~\cite{li2019ease}.
+\note{Such optimization methodologies are driven by the challenges to generate high compositional symbolic without induction in an existing multi-agent environment.}
 
 Figure~\ref{fig:induction} reports the compositionality when training two agents
 in the widely-used listener-speaker referential game~\cite{} for emerging 100
@@ -85,7 +85,7 @@ 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 language
+Yet, few works investigate the emergence of high compositional symbolic language
 \emph{naturally}, i.e., without handcrafted inductions.
 In other words, it is never clear whether \emph{natural}
 environment and agents are sufficient for achieving high compositionality.
@@ -108,8 +108,8 @@ Regarding the theoretical analysis, we propose
 a novel mutual information-based metric to measure the compositionality quantitatively.
 %experimentally
 Regarding the experimental validation, we exploit the relationship between agent
-capacity and the compositionality of \emph{naturally} emergent language
-in our experiments.
+capacity and the compositionality of symbolic language that emerged
+\emph{naturally} in our experiments.
 %two different dedicated experiments, i.e., \note{XXX and XXX, are utilized for XXX}.
 %Regarding the experimental validation, it is conducted on a listener-speaker
 %referential game framework with eliminated unnatural inductions.
@@ -210,16 +210,16 @@ can generate a more compositional language with a higher probability.}
 In this paper, we made the following contributions:
 \begin{itemize}[topsep=0pt,itemsep=0cm]
 \item To our best knowledge, we are the first work to successfully achieve
-high compositional emergent
+high compositional symbolic
 language naturally, without any deliberately handcrafted induction.
-\item We analyze the compositionality of emergent language
+\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
 compositionality quantitatively, which is more reasonable.
 \item We experimentally exploited the relationship between agent
 capacity. Both theoretical analysis and
 experimental results lead to a counter-intuitive conclusion that lower agent
-capacity facilitates the emergence of language with higher
+capacity facilitates the emergence of symbolic language with higher
 compositionality.
 \end{itemize}
 
@@ -229,6 +229,6 @@ Section~\ref{sec:relatedwork} summarizes the related works.
 Section~\ref{sec:thory}
 introduces the experimental setup used in this study. Section~\ref{sec:mis}
 describes our proposed novel mutual-information-based metric for measuring
-the compositionality of emergent language. Section~\ref{sec:exp} gives the
+the compositionality of symbolic language. Section~\ref{sec:exp} gives the
 experimental results of the exploration for the relationship between agent
 capacity and compositionality. Section~\ref{sec:con} concludes this paper.