add title and abstract

AAAI2021/Makefile

@@ -28,7 +28,7 @@ final:
 	ps2pdf14 -dPDFSETTINGS=/prepress final.pdf final-output.pdf
 
 push:
-	git push origin master:master
+	git push gitlab master:master
 
 clean:
 	rm -f *.aux *.bbl *.blg *.log *.out *.pdf *.gz *.fls *.fdb_latexmk

AAAI2021/paper.tex

@@ -89,7 +89,7 @@
 % articles, conjunctions, and prepositions are lower case unless they
 % directly follow a colon or long dash
 
-\title{Characterization Capacity of Agents and Compositionality from Naturally Emergent Communication}
+\title{Revisiting the Natural Emergence of Symbolic Language with Agent Capacity}
 \author{
     %Authors
     % All authors must be in the same font size and format.
@@ -161,18 +161,24 @@
 \maketitle
 
 \begin{abstract}
-Recent advances on symbolic language in neural network based multi-agent systems
-have made great progress in compositionality, which is taken as a key
-feature distinguishing human language from animal language. However, these efforts
-only explored environmental pressures, without realizing the importance of
-characterization capacity of agents. 
-
-In this work, we explore the relationship between the characterization capacity
-of agents and the compositionality of symbolic languages. By proving with
-mutual information theory and verifying with extensive experiments, we made the
-counter-intuitive conclusion that symbolic languages with higher
-compositionality require lower characterization capacity of agents and are
-easier-to-teach. \textcolor{red}{ZD: effects}
+  The natural emergence of symbolic languages with high compositionality has
+  attracted extensive attentions from a broad range of communities. Existing
+  studies only investigated the impacts of \emph{deliberately designed} external
+  environmental factors (e.g., small vocabulary sizes, carefully constructed
+  distractors, and ease-of-teaching), which may be too ideal to exist in the
+  real world, without considering the importance of internal capacity of agents.
+  
+  In this paper, we first reveal and characterize the quantitative relationship
+  between the agent capacity and the compositionality of symbolic language both
+  theoretically and experimentally. The theoretical analysis is built on the MSC
+  (Markov Series Channel) model for the language transmission process and a
+  novel mutual information-based metric for the compositionality. The
+  experiments are conducted on a listener-speaker referential game framework
+  with eliminated external environment factors. 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{abstract}