Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
A
AAAI21_Emergent_language
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
haoyifan
AAAI21_Emergent_language
Commits
ed44e246
Commit
ed44e246
authored
Sep 09, 2020
by
Qi Guo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
up
parent
a5fa4be2
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
25 additions
and
19 deletions
+25
-19
AAAI2021/tex/introduction.tex
+25
-19
No files found.
AAAI2021/tex/introduction.tex
View file @
ed44e246
...
@@ -47,7 +47,7 @@ ease-of-teaching~\cite{}. \note{The basic intuition is that high compositional s
...
@@ -47,7 +47,7 @@ ease-of-teaching~\cite{}. \note{The basic intuition is that high compositional s
language cannot emerge without induction in existing multi-agent environment.
}
language cannot emerge without induction in existing multi-agent environment.
}
Figure~
\ref
{
fig:induction
}
reports the compositionality when training two agents in the widely-used
Figure~
\ref
{
fig:induction
}
reports the compositionality when training two agents in the widely-used
listener-speaker referential game, and it can be observed that
\note
{
the compositionality
listener-speaker referential game, and it can be observed that
\note
{
the compositionality
of emerged symbolic language is extremely low
}
.
of emerged symbolic language is extremely low
without any induction
}
.
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 symbolic language
Yet, few works investigate the emergence of high compositional symbolic language
...
@@ -55,15 +55,19 @@ Yet, few works investigate the emergence of high compositional symbolic language
...
@@ -55,15 +55,19 @@ Yet, few works investigate the emergence of high compositional symbolic language
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.
In this work, we are the first to achieve high compositional
In this paper, we are the first work to achieve high compositional
symbolic language without any handcrafted induction. Concretely, we first
symbolic language without any deliberately handcrafted induction. Concretely,
thoroughly analyze the compositionality of emerged symbolic
by thoroughly analyzing the compositionality of emerged symbolic
language by removing the
\emph
{
deliberately handcrafted
}
language after removing the inductions in a listener-speaker referential game framework,
inductions. Figure~
\ref
{
fig:comp
}
reports the compositionality when train two
we observe that the agent capacity
agents in a listener-speaker referential game. It can be observed that
\note
{
it
plays a key role in improving the compositionality, and thus we can achieve
is challenging to achieve high compositionality without induction as
a high compositional symbilic language in such a natural environment.
xxxxxx
}
. Moreover, we observe that the agent capacity plays a key role in
compositionality, see Figure xxx.
%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
%focus on the natural emergence of high compositional symbolic language
%naturally without any handcrafted induction.
%naturally without any handcrafted induction.
...
@@ -75,16 +79,17 @@ compositionality, see Figure xxx.
...
@@ -75,16 +79,17 @@ compositionality, see Figure xxx.
% xxxxxx}. Moreover, we observe that the agent capacity plays a key role in
% xxxxxx}. Moreover, we observe that the agent capacity plays a key role in
%compositionality, see Figure xxx.
%compositionality, see Figure xxx.
We reveal and characterize the quantitative relationship
The quantitative relationship between the agent capacity and the compositionality
between the agent capacity and the compositionality of symbolic language both
of symbolic language is revealed both theoretically and experimentally.
theoretically and experimentally.
%theoretically
%theoretically
Regarding the theoretical analysis, we use the
Regarding the theoretical analysis, we use the
Markov Series Channel (MSC)~
\cite
{}
to model the language transmission process and a
\note
{
Markov Series Channel (MSC)~
\cite
{}
to model the language transmission process and a
novel mutual information-based metric to measure the compositionality quantitatively.
novel mutual information-based metric to measure the compositionality quantitatively
}
.
%experimentally
%experimentally
Regarding the experimental verification, it is conducted on a listener-speaker
Regarding the experimental validation, two different dedicated experiments, i.e.,
referential game framework with eliminated unnatural inductions.
\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.
Both theoretical analysis and
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 symbolic language with higher
capacity facilitates the emergence of symbolic language with higher
...
@@ -179,8 +184,9 @@ Both theoretical analysis and
...
@@ -179,8 +184,9 @@ Both theoretical analysis and
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
We are the first to successfully achieve high compositional symbolic
\item
To our best knowledge, we are the first work to successfully achieve
language naturally, without any deliberately handcrafted inductions.
high compositional symbolic
language naturally, without any deliberately handcrafted induction.
\item
We thoroughly analyze the compositionality of emerged symbolic language
\item
We thoroughly analyze the compositionality of emerged symbolic language
after removing deliberately handcrafted inductions, and confirm that the agent
after removing deliberately handcrafted inductions, and confirm that the agent
capacity acts as a key factor for compositionality.
capacity acts as a key factor for compositionality.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment