The emergence of symbolic language has always been an important issue,
which attracts attentions from a broad range of communities,
The emergence of symbolic language has always been an important issue,
which attracts attention from a broad range of communities,
including philology~\cite{}, biology~\cite{}, and computer
science~\cite{}. Especially in computer science, efforts in recent years try to explore
science~\cite{}. Especially in computer science, efforts in recent years trying to explore
the emergence of symbolic language in virtual multi-agent environments, where
agents are trained to communicate with neural network based methods such as deep
reinforcement learning~\cite{}.
agents are trained to communicate with neural-network-based methods such as deep
reinforcement learning~\cite{}.
%Such works can be roughly classified into two categories,
%referential game~\cite{} and multi-agent reinforcement learning (MARL)~\cite{}, based on
%the environment setting.
...
...
@@ -21,7 +21,7 @@ given set of simple components (e.g., symbols), can be determined by its
constituent components and the rule combining them~\cite{}.
\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 the productivity,
Compositionality is considered to be a source of productivity,
systematicity, and learnability of language, and the reason why a language with finite
vocabulary can express almost infinite concepts.}
%More recently, measuring the compositionality \note{xxxxx}.}
...
...
@@ -49,7 +49,6 @@ vocabulary can express almost infinite concepts.}
\end{figure}
\begin{table*}[t]
\centering
\small
...
...
@@ -72,21 +71,22 @@ vocabulary can express almost infinite concepts.}
\end{tabular}
\end{table*}
Prior studies focus on achieving high compositional symbolic language
through \emph{deliberately handcrafted} inductions, e.g., memoryless~\cite{},
addtional rewards~\cite{}, constructed loss functions~\cite{}, and
ease-of-teaching~\cite{}. \note{Such optimization methodologies are driven by the challenges to generate high compositional symbolic without induction in existing multi-agent environment.}
Prior studies focus on achieving high compositional symbolic language
through \emph{deliberately handcrafted} inductions, e.g., small vocabulary
sizes~\cite{}, memoryless~\cite{}, additional rewards~\cite{}, constructed loss functions~\cite{}, and
ease-of-teaching~\cite{}. \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 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.}
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
\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.
environment and agents are sufficient for achieving high compositionality.
This paper is the first one to achieve high compositional
symbolic language without any deliberately handcrafted induction. The key observation
...
...
@@ -207,18 +207,18 @@ can generate a higher compositional symbolic 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
\item To our best knowledge, we are the first work to successfully achieve
high compositional symbolic
language naturally, without any deliberately handcrafted induction.
language naturally, without any deliberately handcrafted induction.
\item We analyze the compositionality of emerged symbolic language
after removing deliberately handcrafted inductions.
after removing deliberately handcrafted inductions.
\item We propose a novel mutual information-based metric to measure the
compositionality quantitatively, which is more reasonable.
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 symbolic language with higher
compositionality.
capacity. 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.
\end{itemize}
...
...
@@ -226,7 +226,7 @@ The rest of this paper is arranged as follows.
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 the novel mutual information-based metric for measuring
describes our proposed novel mutual-information-based metric for measuring
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.
