Commit 53ae178a by haoyifan

hao

parent 2800c9e4
...@@ -40,33 +40,18 @@ i.e., hidden layer size ($h_{size}$), from 6 to 100. ...@@ -40,33 +40,18 @@ i.e., hidden layer size ($h_{size}$), from 6 to 100.
Figure~\ref{fig:exp1} reports the supplementally experimental results. Consistent with Figure~\ref{fig:exp1} reports the supplementally experimental results. Consistent with
previous experiments, it can be observed that the mean value of MIS decreases as the value 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. of $h_{size}$ increases, no matter what configuration we take. MIS significantly decreases
Taking the from around 0.8 to less than 0.7 when $h_{size}$ increases from 6 to 100.
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
$h_{size}$ increases from 20 to 40; MIS further reduces to 0.7 when $h_{size}$ Just like we do in the \emph{Experiment} section, we further breakdown our results to show the importance
increases from 40 to 100. of agent capacity for emerging a symbolic language with high compositionality. Figure~\ref{fig:exp2} reports
For different vocabulary sizes, the MIS shares the the ratio of high compositional symbolic language in all emerged languages,
similar behavior. Figure~\ref{fig:exp2} (a) and (b) for $\mathit{MIS}>0.99$ and $\mathit{MIS}>0.9$, respectively.
It is because symbols in low-compositional languages carry semantic information Under these two supplementary configuration, we also find that the ratio of high compositional symbolic languages
about more concepts. As a result, higher capacity is required to characterize the decreases drastically with the increase of $h_{size}$, and such ratio would be closed to zero when agent capacity
complex semantic information for low-compositional language to emerge. comes too large (i.e., $h_{size} > 80$).
In summary, lower agent capacity improves the possibility of
emerging high compositional symbolic language.
\subsection{Ratio of high compositional language.}
We further breakdown our results to investigate the importance of agent capacity
to the compositionality of symbolic language. Figure~\ref{fig:exp2} reports the
ratio of high compositional symbolic language in all emerged languages,
Figure~\ref{fig:exp2} (a) and (b) for $\mathit{MIS}>0.99$ and $\mathit{MIS}>0.9$, respectively. It
can be observed that the ratio of high compositional symbolic languages
decreases drastically with the increase of $h_{size}$.
Taking vocabulary size $|V|=4$ as an example, symbolic languages with
compositionality $\mathit{MIS}>0.99$ take $>$10\% mainly over all the emerged symbolic
languages, when $h_{size}<20$; the ratio reduces to 0\%$\sim$5\% when $h_{size}$
increases to 40; the ratio reduces around 3\% when $h_{size}$ goes beyond 40.
$\mathit{MIS}>0.9$ reports similar results.
Notably, when $h_{size}$ is large enough (e.g., $>40$), high compositional Notably, when $h_{size}$ is large enough (e.g., $>40$), high compositional
symbolic language is hard to emerge in a natural referential game, for symbolic language is hard to emerge in a natural referential game, for
easy-to-emerge low compositional symbolic language is sufficient in scenarios of easy-to-emerge low compositional symbolic language is sufficient in scenarios of
......
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