Skip to content

A
AAAI21_Emergent_language
Commit b5e3fe1b by haoyifan
Options

hao

parent 4b8f9cc8
Showing with 6 additions and 5 deletions
IJCAI2021/tex/introduction.tex
...@@ -7,7 +7,7 @@ including philology, biology, and computer ...@@ -7,7 +7,7 @@ including philology, biology, and computer
science. Especially in computer science, efforts in recent years trying to explore science. 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{kottur-etal-2017-natural,bogin2018emergence,lazaridou2018emergence,choi2018compositional,jaques2019social,mul2019mastering,kharitonov2019egg,labash2020perspective,chaabouni2020compositionality}. reinforcement learning~\cite{kottur-etal-2017-natural,bogin2018emergence,lazaridou2018emergence,choi2018compositional,jaques2019social,mul2019mastering,kharitonov2019egg,labash2020perspective,chaabouni2020compositionality, gupta2020compositionality}.
%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.
...@@ -19,8 +19,8 @@ Compositionality is a principle that determines ...@@ -19,8 +19,8 @@ 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{andreas2018measuring,chaabouni2020compositionality}. 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 ``IJCAI is a conference'' consists of two
meaningful words ``AAAI'' and ``conference'', and a rule for definition (``is''). meaningful words ``IJCAI'' 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,
systematicity, and learnability of language, and the reason why a language with finite systematicity, and learnability of language, and the reason why a language with finite
vocabulary can express almost infinite concepts.} vocabulary can express almost infinite concepts.}
...@@ -66,6 +66,7 @@ vocabulary can express almost infinite concepts.} ...@@ -66,6 +66,7 @@ vocabulary can express almost infinite concepts.}
% \cite{li2019ease}&Population size, resetting all listeners&Quantitative, Speaker\\ % \cite{li2019ease}&Population size, resetting all listeners&Quantitative, Speaker\\
% \cite{chaabouni-etal-2019-word}&Word-order constraints&Not quantitative, Speaker\\ % \cite{chaabouni-etal-2019-word}&Word-order constraints&Not quantitative, Speaker\\
% \cite{chaabouni2020compositionality}&Easier to decode&Quantitative, Speaker\\ % \cite{chaabouni2020compositionality}&Easier to decode&Quantitative, Speaker\\
% \cite{gupta2020compositionality}&structural dependent models&Quantitative, Speaker\\
% \textbf{Ours} & \textbf{None} & \textbf{Quantitative, Speaker+Listener} \\ % \textbf{Ours} & \textbf{None} & \textbf{Quantitative, Speaker+Listener} \\
% \bottomrule % \bottomrule
% \end{tabular} % \end{tabular}
...@@ -74,7 +75,7 @@ vocabulary can express almost infinite concepts.} ...@@ -74,7 +75,7 @@ vocabulary can express almost infinite concepts.}
Prior studies focus on achieving high compositional symbolic language Prior studies focus on achieving high compositional symbolic language
through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{mordatch2017emergence}, through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{mordatch2017emergence},
constructed loss functions~\cite{kharitonov2019egg}, structural input data~\cite{lazaridou2018emergence,evtimova2018emergent}, constructed loss functions~\cite{kharitonov2019egg}, structural input data~\cite{lazaridou2018emergence,evtimova2018emergent},
memoryless~\cite{kottur-etal-2017-natural,li2019ease}, and ease-of-teaching~\cite{li2019ease}. memoryless~\cite{kottur-etal-2017-natural,li2019ease}, ease-of-teaching~\cite{li2019ease}, and structural dependent models~\cite{gupta2020compositionality}.
\note{Such optimization methodologies are driven by the challenges to generate high compositional symbolic 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
......
IJCAI2021/tex/relatedwork.tex
...@@ -7,7 +7,7 @@ Previous works focus on the \emph{deliberately handcrafted} inductions that affe ...@@ -7,7 +7,7 @@ Previous works focus on the \emph{deliberately handcrafted} inductions that affe
compositionality of emergent language. compositionality of emergent language.
Some significant works on studying the environmental inductions on the compositionality of emergent language are summarized in Table~\ref{tab:rel}. Some significant works on studying the environmental inductions on the compositionality of emergent language are summarized in Table~\ref{tab:rel}.
For example, For example,
~\cite{gupta2020compositionality} used a structural dependent agents, i.e., a variational autoencoder, to simulate a speaker-listener pair, and constrained the communication channel into a binary coding sequence. ~\cite{gupta2020compositionality} used a structural dependent models, i.e., a variational autoencoder, to simulate a speaker-listener pair, and constrained the communication channel into a binary coding sequence.
~\cite{kirby2015compression} explored how the pressures for expressivity and compressibility lead the structured language. ~\cite{kirby2015compression} explored how the pressures for expressivity and compressibility lead the structured language.
~\cite{kottur-etal-2017-natural} constrained the vocabulary size and whether the listener has memory to coax the compositionality of the emergent language. ~\cite{kottur-etal-2017-natural} constrained the vocabulary size and whether the listener has memory to coax the compositionality of the emergent language.
~\cite{lazaridou2018emergence} showed that the degree of structure found in the input data affects the emergence of the symbolic language. ~\cite{lazaridou2018emergence} showed that the degree of structure found in the input data affects the emergence of the symbolic language.
......
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