Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
A
AAAI21_Emergent_language
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
haoyifan
AAAI21_Emergent_language
Commits
ea3e53b3
Commit
ea3e53b3
authored
Sep 17, 2020
by
haoyifan
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fsd
parent
d4c38c9d
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
20 additions
and
13 deletions
+20
-13
AAAI2021/tex/appendix.tex
+20
-13
No files found.
AAAI2021/tex/appendix.tex
View file @
ea3e53b3
...
...
@@ -37,6 +37,24 @@ Specifically, with the configuration of: a)$|M_0|=5,|M_1|=3,|V|=10$ and b)$|M_0|
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.
\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}
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
...
...
@@ -44,6 +62,7 @@ of $h_{size}$ increases, no matter what configuration we take. MIS significantly
from around 0.8 to less than 0.7 when
$
h
_{
size
}$
increases from 6 to 100.
Just like we do in the
\emph
{
Experiment
}
section, we further breakdown our results to show the importance
of agent capacity for emerging a symbolic language with high compositionality. Figure~
\ref
{
fig:exp2
}
reports
the ratio of high compositional symbolic language in all emerged languages,
...
...
@@ -53,6 +72,7 @@ decreases drastically with the increase of $h_{size}$, and that such ratio would
comes too large (i.e.,
$
h
_{
size
}
>
80
$
).
For these two supplementary sets of data, we also perform
$
\chi
^
2
$
test to check the statistical
significance between the high compositionality and agent
capacity. Table~
\ref
{
tab:exp10
}
reports the
$
\chi
^
2
$
test results for
...
...
@@ -62,19 +82,6 @@ the high compositionality has a statistical significance related to agent
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}
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment