s464900/gonito
1
0
Fork 0
forked from filipg/gonito
Code Issues Pull Requests Projects Releases Wiki Activity

update datech presentation

Browse Source
This commit is contained in:
Filip Gralinski 2017-05-29 23:24:12 +02:00
parent 372d814983
commit 0ed348fc4f
3 changed files with 66 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Handler/Presentation.hs
View File

@ -37,6 +37,8 @@ getPresentation4RealR = do
presentationLayout $(widgetFile "presentation-4real") presentationLayout $(widgetFile "presentation-4real")
getPresentationDATeCH2017R = do getPresentationDATeCH2017R = do
readme <- challengeReadme sampleChallengeName
sampleLeaderboard <- getSampleLeaderboard sampleChallengeName'
presentationLayout $(widgetFile "presentation-datech-2017") presentationLayout $(widgetFile "presentation-datech-2017")

4
static/css/impress-demo.css
View File

@ -49,6 +49,10 @@ time, mark, audio, video {
vertical-align: baseline; vertical-align: baseline;
} }
.stats tr td {
padding: 12px
}
h1 { h1 {
padding-bottom: 12px; padding-bottom: 12px;
font-weight: bold; font-weight: bold;

61
templates/presentation-datech-2017.hamlet
View File

@ -34,4 +34,63 @@
<li>18th century till today <li>18th century till today
<li>mostly Polish <li>mostly Polish
<ul> <ul>
<li>… also German <li>… (also German if you're interested — 350K publications)
<div class="step slide" data-x="0" data-y="3000">
<h2>The challenge…
<div style="font-size: 50%" class="readme">
^{readme}
<p>Available at <a href="http://gonito.net/retroc">Gonito.net platform</a> or just:
<pre>
git clone git://gonito.net/retroc
<div class="step slide" data-x="1000" data-y="3000">
<p>Core assumption
<ul>
<li>the temporal classifier will be used to date historical texts with no publication date given in metadata
<h2>Assumptions
<ul>
<li>random sample of the whole corpus
<ul>
<li>stable random so the corpus can grow
<li>test set balanced for years (1814-2013)
<ul>
<li>but train set — not
<li><b>different</b> sources used in the train and test set
<li>500-word text snippets
<li>OCR noise kept as it is
<div class="step slide" data-x="2000" data-y="3000">
<h2>RetroC(2) in numbers
<p>Number of texts:
<table class="stats">
<tr>
<th>
<th>train
<th>dev-0
<th>dev-1
<th>test
<tr>
<td>RetroC
<td>40K
<td>9.9K
<td>-
<td>10K
<tr>
<td>RetroC2
<td>107.4K
<td>20K
<td>11.5K
<td>14.2K
<div class="step slide" style="height: 800px;" data-x="0" data-y="4000">
<h2>Current status…
<div style="font-size: 50%">
^{sampleLeaderboard}