Commit c26556f4 by Zidong Du

abstract

parent 52ace7e5
......@@ -50,7 +50,7 @@ the emergence of language and even intelligence among our pre-human ancestors.
Yet, few works investigate the emergence of symbolic language with high
compositionality in \emph{naturally} (i.e., without \emph{deliberately
compositionality \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.
In this work, we focus on generating high compositional symbolic language
......@@ -58,9 +58,23 @@ naturally without any ``human'' 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{xxxxxxxx}.
Thus, it is challenging to achieve high compositionality without induction.
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.
In this work, we reveal and characterize the quantitative relationship
between the agent capacity and the compositionality of symbolic language both
theoretically and experimentally.
%theoretically
Regarding the theoretical analysis, it is conduct based on the MSC
(Markov Series Channel) model for the language transmission process and a
novel mutual information-based metric for the compositionality.
%experimentally
Regarding the experimental verification, it is conducted on a listener-speaker referential game framework
with eliminated unnatural inductions.
================
......
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