Commit 26ccb660 by Qi Guo

up

parent e1ef3584
......@@ -95,7 +95,7 @@
% articles, conjunctions, and prepositions are lower case unless they
% directly follow a colon or long dash
\title{Revisiting the Natural Emergence of Symbolic Language with Agent Capacity}
\title{Enabling the Emergence of Symbolic Language without Handcrafted Inductions}
\author{
%Authors
% All authors must be in the same font size and format.
......@@ -177,7 +177,7 @@
inductions.
In this paper, we are the first to successfully achieve high compositional symbolic
language in a purely \emph{natural} manner.
language in a \emph{natural} manner without handcrafted inductions.
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
......@@ -194,7 +194,7 @@
experimental results lead to a counter-intuitive conclusion that lower agent
capacity facilitates the emergence of symbolic language with higher
compositionality. \note{Based on our conclusion, we can generate higher
compositional symbolic language with a high probability.}
compositional symbolic language with a higher probability.}
% The natural emergence of symbolic languages with high compositionality has
......
\section{Introduction}
\label{sec:introduction}
The emergence of symbolic language has always been an important and controversial
issue. This problem attracts attentions from a broad range of communities,
The emergence of symbolic language has always been an important issue,
which attracts attentions 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
the emergence of symbolic language in virtual, multi-agent environments, where
agents are trained to communicate with neural network based method, i.e., deep
reinforcement learning~\cite{}. For example, \note{XXXX}
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{}.
%Such works can be roughly classified into two categories,
%referential game~\cite{} and multi-agent reinforcement learning (MARL)~\cite{}, based on
%the environment setting.
Compositionality is widely used and
taken as an important metric to evaluate the emerged symbolic language.
Originally, compositionality is a principle that
whether the meaning of a complex expression (e.g, phase), which is assembled out of the
The quality of emergent symbolic language is typically measured by its \emph{compositionality}.
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 rules that combines 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'').}
More recently, measuring the compositionality \note{xxxxx}.
meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is'').
More recently, measuring the compositionality \note{xxxxx}.}
%It
......@@ -41,28 +40,41 @@ More recently, measuring the compositionality \note{xxxxx}.
\label{fig:symbols}
\end{figure}
Prior studies focus on achieving high compositionality
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
ease-of-teaching~\cite{}. \note{xxxxxxx}
However, these unnatural inductions prevent us from better understanding the mystery of
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
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
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 \emph{deliberately
handcrafted} inductions.
As a results, it is never clear whether \emph{natural}
environment and agent are sufficient for compositionality.
\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.
In this work, we focus on the natural emergence of high compositional symbolic language
naturally without any handcrafted induction.
Initially, we thoroughly analyze the compositionality of emerged symbolic
language after removing the \emph{deliberately handcrafted}
In this work, we are the first to achieve high compositional
symbolic language without any handcrafted induction. Concretely, we first
thoroughly analyze the compositionality of emerged symbolic
language by removing the \emph{deliberately handcrafted}
inductions. Figure~\ref{fig:comp} reports the compositionality when train two
agents in a listener-speaker referential game. It can be observed that \note{it
is challenging to achieve high compositionality without induction as
xxxxxx}. Moreover, we observe that the agent capacity plays a key role in
compositionality, see Figure xxx.
%focus on the natural emergence of high compositional symbolic language
%naturally without any handcrafted induction.
%Initially, we thoroughly analyze the compositionality of emerged symbolic
%language after removing the \emph{deliberately handcrafted}
%inductions. Figure~\ref{fig:comp} reports the compositionality when train two
%agents in a listener-speaker referential game. It can be observed that \note{it
% is challenging to achieve high compositionality without induction as
% xxxxxx}. Moreover, we observe that the agent capacity plays a key role in
%compositionality, see Figure xxx.
We reveal and characterize the quantitative relationship
between the agent capacity and the compositionality of symbolic language both
theoretically and experimentally.
......
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