Skip to content

A
AAAI21_Emergent_language
Commit c7310c91 by Ruizhi Chen
Options

添加引用

parent dace1bd8
Showing with 16 additions and 16 deletions
AAAI2021/tex/introduction.tex
...@@ -3,11 +3,11 @@ ...@@ -3,11 +3,11 @@
The emergence of language has always been an important issue, The emergence of language has always been an important issue,
which attracts attention from a broad range of communities, 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 science~\cite{}. Especially in computer science, efforts in recent years trying to explore
the emergent language in virtual multi-agent environments, where the emergent language in virtual multi-agent environments, where
agents are trained to communicate with neural-network-based methods such as deep 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, %Such works can be roughly classified into two categories,
%referential game~\cite{} and multi-agent reinforcement learning (MARL)~\cite{}, based on %referential game~\cite{} and multi-agent reinforcement learning (MARL)~\cite{}, based on
%the environment setting. %the environment setting.
...@@ -18,7 +18,7 @@ The quality of emergent language is typically measured by its ...@@ -18,7 +18,7 @@ The quality of emergent language is typically measured by its
Compositionality is a principle that determines Compositionality is a principle that determines
whether the meaning of a complex expression (e.g, phrase), which is assembled out of a 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 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 \note{For example, the expression ``AAAI is a conference'' consists of two
meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is''). meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is'').
Compositionality is considered to be a source of productivity, Compositionality is considered to be a source of productivity,
...@@ -40,9 +40,9 @@ vocabulary can express almost infinite concepts.} ...@@ -40,9 +40,9 @@ vocabulary can express almost infinite concepts.}
\begin{figure}[t] \begin{figure}[t]
\centering \centering
\includegraphics[width=\columnwidth]{fig/Figure1_motivation.pdf} \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 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 seldom emerged (e.g., $<5\%$ for compositionality $>0.99$). Moreover, varying
the vocabulary size does not affect the compositionality notably.} the vocabulary size does not affect the compositionality notably.}
\label{fig:induction} \label{fig:induction}
...@@ -71,11 +71,11 @@ vocabulary can express almost infinite concepts.} ...@@ -71,11 +71,11 @@ vocabulary can express almost infinite concepts.}
\end{tabular} \end{tabular}
\end{table*} \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{}, through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{},
constructed loss functions~\cite{}, structural input data~\cite{}, constructed loss functions~\cite{kharitonov2019egg}, structural input data~\cite{lazaridou2018emergence,evtimova2018emergent},
memoryless~\cite{}, and ease-of-teaching~\cite{}. 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 language without induction in an existing multi-agent environment.} \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 Figure~\ref{fig:induction} reports the compositionality when training two agents
in the widely-used listener-speaker referential game~\cite{} for emerging 100 in the widely-used listener-speaker referential game~\cite{} for emerging 100
...@@ -85,7 +85,7 @@ without any induction. Moreover, varying ...@@ -85,7 +85,7 @@ 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 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. 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. \emph{naturally}, i.e., without handcrafted inductions.
In other words, it is never clear whether \emph{natural} 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.
...@@ -108,8 +108,8 @@ Regarding the theoretical analysis, we propose ...@@ -108,8 +108,8 @@ Regarding the theoretical analysis, we propose
a novel mutual information-based metric to measure the compositionality quantitatively. a novel mutual information-based metric to measure the compositionality quantitatively.
%experimentally %experimentally
Regarding the experimental validation, we exploit the relationship between agent Regarding the experimental validation, we exploit the relationship between agent
capacity and the compositionality of \emph{naturally} emergent language capacity and the compositionality of symbolic language that emerged
in our experiments. \emph{naturally} in our experiments.
%two different dedicated experiments, i.e., \note{XXX and XXX, are utilized for XXX}. %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 %Regarding the experimental validation, it is conducted on a listener-speaker
%referential game framework with eliminated unnatural inductions. %referential game framework with eliminated unnatural inductions.
...@@ -210,16 +210,16 @@ can generate a more compositional language with a higher probability.} ...@@ -210,16 +210,16 @@ can generate a more compositional language with a higher probability.}
In this paper, we made the following contributions: In this paper, we made the following contributions:
\begin{itemize}[topsep=0pt,itemsep=0cm] \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 emergent high compositional symbolic
language naturally, without any deliberately handcrafted induction. 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. after removing deliberately handcrafted inductions.
\item We propose a novel mutual information-based metric to measure the \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 \item We experimentally exploited the relationship between agent
capacity. Both theoretical analysis and capacity. Both theoretical analysis and
experimental results lead to a counter-intuitive conclusion that lower agent 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. compositionality.
\end{itemize} \end{itemize}
...@@ -229,6 +229,6 @@ Section~\ref{sec:relatedwork} summarizes the related works. ...@@ -229,6 +229,6 @@ Section~\ref{sec:relatedwork} summarizes the related works.
Section~\ref{sec:thory} Section~\ref{sec:thory}
introduces the experimental setup used in this study. Section~\ref{sec:mis} introduces the experimental setup used in this study. Section~\ref{sec:mis}
describes our proposed novel mutual-information-based metric for measuring 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 experimental results of the exploration for the relationship between agent
capacity and compositionality. Section~\ref{sec:con} concludes this paper. capacity and compositionality. Section~\ref{sec:con} concludes this paper.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment