Commit 297af875 by haoyifan

o

h
parent b5e3fe1b
...@@ -49,28 +49,28 @@ vocabulary can express almost infinite concepts.} ...@@ -49,28 +49,28 @@ vocabulary can express almost infinite concepts.}
\end{figure} \end{figure}
%\begin{table*}[t] \begin{table*}[t]
% \centering \centering
% \small \small
% \caption{Handcrafted inductions in related works.} \caption{Handcrafted inductions in related works.}
% \label{tab:rel} \label{tab:rel}
% \begin{tabular}{llllll} \begin{tabular}{llllll}
% \toprule \toprule
% Works & Handcrafted induction & Compositionality\\ Works & Handcrafted induction & Compositionality\\
% \midrule \midrule
% \cite{kirby2015compression}&Expressivity and compressibility&Not quantitative, Speaker\\ \cite{kirby2015compression}&Expressivity and compressibility&Not quantitative, Speaker\\
% \cite{kottur-etal-2017-natural}&Listener's memory&Not quantitative, Speaker\\ \cite{kottur-etal-2017-natural}&Listener's memory&Not quantitative, Speaker\\
% \cite{choi2018compositional}&Maximum message length&Not quantitative, Speaker+Listener\\ \cite{choi2018compositional}&Maximum message length&Not quantitative, Speaker+Listener\\
% \cite{lazaridou2018emergence}&Structure of input data&Quantitative, Speaker\\ \cite{lazaridou2018emergence}&Structure of input data&Quantitative, Speaker\\
% \cite{evtimova2018emergent}&Multi-modal scenarios&Quantitative, Speaker\\ \cite{evtimova2018emergent}&Multi-modal scenarios&Quantitative, Speaker\\
% \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\\ \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}
% \end{table*} \end{table*}
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},
......
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