Commit 2800c9e4 by haoyifan

hfa

parent 24ebf3bf
\documentclass[11pt,b5paper,onecolumn]{article}
\begin{figure}[t]
\centering \includegraphics[width=0.99\columnwidth]{fig/Appendix_Figure1_MIS.pdf}
\caption{Compositionality of symbolic language under different parameters
($[\mu-\sigma,\mu+\sigma]$, where $\mu$ is the mean value and $\sigma$ is
the standard deviation).}
\label{fig:exp1}
\end{figure}
\begin{figure}[t]
\centering \includegraphics[width=0.99\columnwidth]{fig/Appendix_Figure2_Ratio.pdf}
\caption{The ratio of high compositional language. (a) $MIS>0.99$. (b)
$MIS>0.9$. }
\label{fig:exp2}
\end{figure}
\begin{table}[b] \begin{table}[b]
\centering \centering
\small \small
...@@ -48,15 +29,19 @@ ...@@ -48,15 +29,19 @@
\section{Appendix} \section{Appendix}
\label{sec:exp} \label{sec:exp}
We exploit the relationship between agent capacity and the compositionality of We add two sets of experimental results to further verify the relationship between
symbolic language that emerged in our natural referential game. agent capacity and the compositionality of symbolic language that emerged in our natural referential game.
For various configuration of As a supplement to the \emph{Experiments} section, these two sets of data (coresponding to two
vocabulary size, we fix $|M_0|=|M_1|=3$ and train the speaker-listener agents to emerge symbolic kinds of configuration) are used to prove that the relationship is independent of configuration.
language when varying the agent capacities, i.e., hidden layer size Specifically, with the configuration of: a)$|M_0|=5,|M_1|=3,|V|=10$ and b)$|M_0|=4,|M_1|=4,|V|=10$,
($h_{size}$), from 6 to 100. we train the speaker-listener agents to emerge symbolic language when varying the agent capacities,
i.e., hidden layer size ($h_{size}$), from 6 to 100.
Figure~\ref{fig:exp1} reports the experimental results. It can be observed that Figure~\ref{fig:exp1} reports the supplementally experimental results. Consistent with
the mean value of MIS decreases as the value of $h_{size}$ increases. Taking the previous experiments, it can be observed that the mean value of MIS decreases as the value
of $h_{size}$ increases, no matter what configuration we take.
Taking the
configuration of vocabulary size $|V|=10$ as an example, the mean value of MIS configuration of vocabulary size $|V|=10$ as an example, the mean value of MIS
is around 0.8 when $h_{size}\le 20$; MIS significantly decreases to 0.75 when is around 0.8 when $h_{size}\le 20$; MIS significantly decreases to 0.75 when
$h_{size}$ increases from 20 to 40; MIS further reduces to 0.7 when $h_{size}$ $h_{size}$ increases from 20 to 40; MIS further reduces to 0.7 when $h_{size}$
...@@ -98,3 +83,21 @@ $\mathit{MIS}>0.99$ and $\mathit{MIS}>0.9$, respectively. It can be observed tha ...@@ -98,3 +83,21 @@ $\mathit{MIS}>0.99$ and $\mathit{MIS}>0.9$, respectively. It can be observed tha
for different vocabulary sizes, the p-value is always less than 0.05, which means for different vocabulary sizes, the p-value is always less than 0.05, which means
the high compositionality has a statistical significance related to agent the high compositionality has a statistical significance related to agent
capacity. capacity.
\begin{figure}[t]
\centering \includegraphics[width=0.99\columnwidth]{fig/Appendix_Figure1_MIS.pdf}
\caption{Compositionality of symbolic language under different parameters
($[\mu-\sigma,\mu+\sigma]$, where $\mu$ is the mean value and $\sigma$ is
the standard deviation).}
\label{fig:exp1}
\end{figure}
\begin{figure}[t]
\centering \includegraphics[width=0.99\columnwidth]{fig/Appendix_Figure2_Ratio.pdf}
\caption{The ratio of high compositional language. (a) $MIS>0.99$. (b)
$MIS>0.9$. }
\label{fig:exp2}
\end{figure}
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