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
53ae178a
Commit
53ae178a
authored
Sep 17, 2020
by
haoyifan
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
hao
parent
2800c9e4
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
12 additions
and
27 deletions
+12
-27
AAAI2021/tex/appendix.tex
+12
-27
No files found.
AAAI2021/tex/appendix.tex
View file @
53ae178a
...
...
@@ -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
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
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
}$
increases from 40 to 100.
For different vocabulary sizes, the MIS shares the
similar behavior.
It is because symbols in low-compositional languages carry semantic information
about more concepts. As a result, higher capacity is required to characterize the
complex semantic information for low-compositional language to emerge.
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.
of
$
h
_{
size
}$
increases, no matter what configuration we take. MIS significantly decreases
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,
Figure~
\ref
{
fig:exp2
}
(a) and (b) for
$
\mathit
{
MIS
}
>
0
.
99
$
and
$
\mathit
{
MIS
}
>
0
.
9
$
, respectively.
Under these two supplementary configuration, we also find that the ratio of high compositional symbolic languages
decreases drastically with the increase of
$
h
_{
size
}$
, and such ratio would be closed to zero when agent capacity
comes too large (i.e.,
$
h
_{
size
}
>
80
$
).
Notably, when
$
h
_{
size
}$
is large enough (e.g.,
$
>
40
$
), high compositional
symbolic language is hard to emerge in a natural referential game, for
easy-to-emerge low compositional symbolic language is sufficient in scenarios of
...
...
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