<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="http://coco-lab.org/Elgg/news/rss/rssstyles.xsl"/?>
<rss version='2.0'   xmlns:dc='http://purl.org/dc/elements/1.1/'>
<channel xml:base='http://coco-lab.org/Elgg//weblog/'>
    <title><![CDATA[timo : RSS Feed]]></title>
    <description><![CDATA[RSS Feed showing user for timo using the Elgg software]]></description>
    <generator>Elgg</generator>
    <link>http://coco-lab.org/Elgg/activity/user/timo/summary/page+page_comment/all/1</link>        
        <item>
            <title><![CDATA[Literature Day ZWEI]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Literature+Day+ZWEI</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Literature+Day+ZWEI</guid>
            <pubDate>07/20/08 20:51</pubDate>
            <description><![CDATA[<p>vorl&auml;ufige Terminvorschl&auml;ge: 24. oder 28. Juli (Meinungen dazu bitte bis 21. Juli) </p><h2>Literaturliste</h2><ol><li>Mangu, Brill, Stolcke (2000): <a href="http://arxiv.org/abs/cs/0010012">Finding consensus in speech recognition: word error minimization and other applications of confusion networks</a>. [Timo, +]<br /></li><li>Wilson, Wilson (2006): <a href="http://people.ucsc.edu/~mlwilson/publications/Turn_Taking.pdf">An oscillator model of the timing of turn-taking</a>. [David]</li><li>was zu SDS-Architektur?<br /></li></ol>]]></description>
        </item>        
        <item>
            <title><![CDATA[Literature Day ZWEI]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Literature+Day+ZWEI</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Literature+Day+ZWEI</guid>
            <pubDate>07/14/08 15:42</pubDate>
            <description><![CDATA[<p>vorl&auml;ufige Terminvorschl&auml;ge: 24. oder 28. Juli (Meinungen dazu bitte bis 21. Juli) </p><h2>Literaturliste</h2><ol><li>Mangu, Brill, Stolcke (2000): <a href="http://arxiv.org/abs/cs/0010012">Finding consensus in speech recognition: word error minimization and other applications of confusion networks</a> [Timo, +]<br /></li><li>Oszillator-im-Hirn-Kram [David]</li><li>was zu SDS-Architektur?<br /></li></ol>]]></description>
        </item>        
        <item>
            <title><![CDATA[Higgins]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Higgins</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Higgins</guid>
            <pubDate>07/14/08 09:44</pubDate>
            <description><![CDATA[<p>Higgins-Howto&nbsp;</p><ul><li>Mozart &uuml;ber Synaptic installieren:</li><ul><li>mozart</li><li>mozart-gtk</li><li>mozart-stdlib<br /></li></ul><li>Higgins aus svn+ssh://helios/projekte/inpro/INPRO_SVN/Code/Higgins auschecken.<br /></li><li>export HIGGINS_RUN=&lt;pfad-zu-higgins&gt; (am besten gleich in die .bashrc schreiben, dann wei&szlig; es jedes neu ge&ouml;ffnete terminal)<br /></li><li>ozengine launcher/Launcher.exe applications/Numbers/numbers.higgins</li><li>von da aus die einzelnen Module starten (die Inspektoren gehen noch nicht)</li><li>f&uuml;r die Sphinx-Anbindung:</li><ul><li>svn update in Eclipse (die Pakete hei&szlig;en de.cocolab.inpro.higgins.*)</li><li>die sind jetzt veraltet, oder was?<br /></li><li>TODO: Build-Pfad anpassen, noch irgendwas einbinden<br /></li></ul><li>voil&agrave;</li></ul>]]></description>
        </item>        
        <item>
            <title><![CDATA[Higgins]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Higgins</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Higgins</guid>
            <pubDate>07/14/08 09:42</pubDate>
            <description><![CDATA[<p>Higgins-Howto&nbsp;</p><ul><li>Mozart &uuml;ber Synaptic installieren:</li><ul><li>mozart</li><li>mozart-gtk</li><li>mozart-stdlib<br /></li></ul><li>Higgins aus svn+ssh://helios/projekte/inpro/INPRO_SVN/Code/Higgins auschecken.<br /></li><li>export HIGGINS_RUN=&lt;pfad-zu-higgins&gt; (am besten gleich in die .bashrc schreiben, dann wei&szlig; es jedes neu ge&ouml;ffnete terminal)<br /></li><li>ozengine launcher/Launcher.exe applications/Numbers/numbers.higgins</li><li>von da aus die einzelnen Module starten (die Inspektoren gehen noch nicht)</li><li>f&uuml;r die Sphinx-Anbindung:</li><ul><li>svn update in Eclipse (die Pakete hei&szlig;en de.cocolab.inpro.higgins.*)</li><li>TODO: Build-Pfad anpassen, noch irgendwas einbinden<br /></li></ul><li>voil&agrave;</li></ul>]]></description>
        </item>        
        <item>
            <title><![CDATA[Higgins]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Higgins</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Higgins</guid>
            <pubDate>04/11/08 14:35</pubDate>
            <description><![CDATA[<p>Higgins-Howto&nbsp;</p><ul><li>Mozart &uuml;ber Synaptic installieren:</li><ul><li>mozart</li><li>mozart-gtk</li><li>mozart-stdlib<br /></li></ul><li>Higgins aus svn+ssh://helios/projekte/inpro/INPRO_SVN/Code/Higgins auschecken.<br /></li><li>export HIGGINS_RUN=&lt;pfad-zu-higgins&gt; (am besten gleich in die .bashrc schreiben, dann wei&szlig; es jedes neu ge&ouml;ffnete terminal)<br /></li><li>ozengine launcher/Launcher.exe Potsdam/number.higgins</li><li>von da aus die einzelnen Module starten (die Inspektoren gehen noch nicht)</li><li>f&uuml;r die Sphinx-Anbindung:</li><ul><li>svn update in Eclipse (die Pakete hei&szlig;en de.cocolab.inpro.higgins.*)</li><li>TODO: Build-Pfad anpassen, noch irgendwas einbinden<br /></li></ul><li>voil&agrave;</li></ul>]]></description>
        </item>        
        <item>
            <title><![CDATA[hours 20080407]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/hours+20080407</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/hours+20080407</guid>
            <pubDate>04/09/08 09:22</pubDate>
            <description><![CDATA[<ul><li>Meeting notes 2008-04-07<br /></li><li>present: Michaela, David, Timo</li><li>TOP 1: Timo hat sich auf keine Professur beworben und wird das auch in vorerst nicht tun.</li><li>TOP 2: roadmap until july</li><ul><li>working (albeit simple) automatic system</li><ul><li>ASR, some slot filling </li><li>dialogue management </li><li>domain reasoning</li><li>information fission (concept to action)</li><li>concept to GUI action, GUI control</li></ul><li>working (more complex) WOZ-system</li><ul><li>pento server (GUI control)</li><li>wizard guidelines detailing abilities of the simulated system<br /></li></ul><li>modules shared by both tasks</li><ul><li>TTS (actually, concept to speech)<br /></li><li>pento-client </li></ul></ul><li>TOP 3: variables to control domain complexity</li><ul><li>user</li><ul><li>has solution? </li><ul><li>solution numbered?</li></ul><li>elephant priming?</li></ul><li>task</li><ul><li>shared visual space?</li><ul><li>tiles visible (or system describes which tile comes next, together with unnumbered solution)</li><li>board visible?</li></ul><li>random placement of tiles?</li><li>correct orientation of tiles?</li><li>coloring of the tiles? </li><li>block-markings on board and tiles? (may trigger different naming of tiles)</li><li>continuous/discrete actions? (cursor and tiles visible while they are being dragged)</li><li>must the task be completed or should the system play the last (three) moves on its own? </li></ul><li>system</li><ul><li>has solution?</li><ul><li>allow for wrong moves by the user? how to cope with user errors?<br /></li></ul><li>free/slot filling</li><li>allows for overanswering?</li><li>continuous/discrete actions? (ability to disrupt GUI actions, only necessary for the continuous task, the continuous task could still be coupled with discrete actions of the system, but would likely lead to bad usability)</li><li>helpfulness? (somewhat coupled with has-solution and domain knowledge) </li></ul></ul></ul>]]></description>
        </item>        
        <item>
            <title><![CDATA[Higgins]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/Higgins</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/Higgins</guid>
            <pubDate>04/01/08 14:12</pubDate>
            <description><![CDATA[<p>Higgins-Howto&nbsp;</p><ul><li>Mozart &uuml;ber Synaptic installieren</li><li>Higgins aus svn+ssh://helios/projekte/inpro/INPRO_SVN/Code/Higgins auschecken.<br /></li><li>export HIGGINS_RUN=`pwd`</li><li>ozengine launcher/Launcher.exe Potsdam/number.higgins</li><li>voil&agrave;</li></ul>]]></description>
        </item>        
        <item>
            <title><![CDATA[experiment definitions]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/experiment+definitions</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/experiment+definitions</guid>
            <pubDate>02/26/08 15:26</pubDate>
            <description><![CDATA[<table border="1"  cellspacing="2"  cellpadding="2"  style="text-align: left; width: 100%">   <tbody>     <tr>       <td>&nbsp;</td>       <td>unit</td>       <td>selection</td>       <td>class</td>     </tr>     <tr>       <td>bc.utt</td>       <td>word</td>       <td>annot. EOU</td>       <td>EOT</td>     </tr>     <tr>       <td>3-<span style="color:red; font-weight: bold">X</span>ms</td>       <td>word</td>       <td>pause&nbsp;&ge;&nbsp;<span style="color:red; font-weight: bold">X</span> ms</td>       <td>EOT</td>     </tr>     <tr>       <td>us</td>       <td>word</td>       <td>any</td>       <td>EO<span style="font-weight: bold">U</span></td>     </tr>     <tr>       <td>2 (aw)</td>       <td>word</td>       <td>any</td>       <td>EOT</td>     </tr>     <tr>       <td>af.bin-<span style="color:red; font-weight: bold">X</span>ms-<span style="font-weight: bold; color: blue">n</span>s-now <br />(was: 1, 4)<br /></td>       <td>frane</td>       <td>any</td>       <td>vicinity of <span style="color:red; font-weight: bold">X</span> ms <br /> incl.(<span style="font-weight: bold; color: blue">n</span>)/excl.       <br /> following silence</td>     </tr>   </tbody> </table> ]]></description>
        </item>        
        <item>
            <title><![CDATA[experiment definitions]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/experiment+definitions</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/experiment+definitions</guid>
            <pubDate>02/26/08 15:20</pubDate>
            <description><![CDATA[<table border="1"  cellspacing="2"  cellpadding="2"  style="text-align: left; width: 100%">   <tbody>     <tr>       <td>&nbsp;</td>       <td>unit</td>       <td>selection</td>       <td>class</td>     </tr>     <tr>       <td>bc.utt</td>       <td>word</td>       <td>annot. EOU</td>       <td>EOT</td>     </tr>     <tr>       <td>3-<span style="color:red; font-weight: bold">X</span>ms</td>       <td>word</td>       <td>pause&nbsp;&ge;&nbsp;<span style="color:red; font-weight: bold">X</span> ms</td>       <td>EOT</td>     </tr>     <tr>       <td>us</td>       <td>word</td>       <td>any</td>       <td>EO<span style="font-weight: bold">U</span></td>     </tr>     <tr>       <td>2 (aw)</td>       <td>word</td>       <td>any</td>       <td>EOT</td>     </tr>     <tr>       <td>af.bin-<span style="color:red; font-weight: bold">X</span>ms-<span style="font-weight: bold; color: blue">n</span>s-now</td>       <td>frane</td>       <td>any</td>       <td>vicinity of <span style="color:red; font-weight: bold">X</span> ms <br /> incl.(<span style="font-weight: bold; color: blue">n</span>)/excl.       <br /> following silence</td>     </tr>   </tbody> </table> ]]></description>
        </item>        
        <item>
            <title><![CDATA[hours 20071126]]></title>
            <link>http://coco-lab.org/Elgg/timo/page/hours+20071126</link>
            <guid isPermaLink="true">http://coco-lab.org/Elgg/timo/page/hours+20071126</guid>
            <pubDate>11/26/07 17:09</pubDate>
            <description><![CDATA[<ul><li>present: Michaela, David, Timo</li><li>Allgemeines:</li><ul><li>&uuml;bliche Anwesenheit in Golm</li><ul><li>es ist generell ganz nett, abends bevor man geht noch kurz zu sagen, wann man das n&auml;chstemal kommt </li></ul><ul><li>David: Mo, (Di), Fr</li><li>Timo: Meeting-Montage, Di, (Mi), Do</li><li>Michaela: mal abwarten wie sch&ouml;n ihre Wohnung wird</li></ul><li>ansonsten nicht scheuen, auch per IM/E-Mail zu kommunizieren (IM-Status richtig einstellen)</li><li>zur besseren Kommunikation im Institut gibt es realistisch drei M&ouml;glichkeiten</li><ul><li>Coffeetalks/Vormittagstalks</li><li>unregelm&auml;&szlig;ige Postersessions</li><li>h&auml;ufigeres Kolloquium mit internen Vortr&auml;gen</li><li>dabei geht es nicht nur um den wissenschaflichen Austausch, sondern auch um allgemein organisatorische Dinge. <br /></li><li>David schreibt ne Mail an die Professoren um zu erfahren, ob ansonsten auch Interesse an mehr Austausch besteht</li></ul><li>Urlaubsplanung zu Weihnachten:</li><ul><li>Michaela: wei&szlig; nicht genau, zwischen den Jahren in Augsburg, danach wohl Umzug</li><li>David: 21.-26. Dezember, ansonten strebsam</li><li>Timo: faul vom 21. Dezember bis 4. Januar in Hamburg/Kiel</li></ul><ul><li>also m&uuml;ssen unsere Ergebnisse so weit wie m&ouml;glich schon vor Weihnachten stehen</li></ul></ul><li>Paper</li><ul><li>Selling point: Syntax (esp. incrementally)</li><li>What&#39;s a turn? <br /></li><ul><li>we should probably distinguish more between turn yield and turn hold instead of just EOT</li><li>we want to be able to try different experiments, thus our feature vectors will be &quot;verdongelt&quot; afterwards and must be able to be identified in different settings</li><ul><li>Syntax: dialogID, wordID</li><li>Prosody: dialogID, channel, time</li></ul><li>currently, the mapping in *words.csv uses information from MSaligned/ and from /projekte/korpora/orig-korpora/pennTreebank/dysfl/mgd/swbd</li><li>Timo will review the scripts that create the mapping until next tuesday</li></ul><li>class feature</li><ul><li><em>n</em> words still missing<br /></li><li>time to EOT (from end of this word)<br /></li><li>make it easier for the parser:</li><ul><li>possible completion points (PCP?)<br /></li></ul><li>I&#39;m still not sure we completely acknowledge the fact that we are in some areas dealing with EOT and sometimes with EOU. </li></ul><li>features</li><ul><li>additional features<br /></li><ul><li>expected POS after current word </li></ul></ul><ul><ul><li>flags: seen a verb? how many NPs? <br /></li></ul><li>better documentation of our features </li></ul><li>Gold standard</li><ul><li>how do we compare to the Penn treebank data directly <br /></li><ul><li>how would that data have to be &quot;incrementalized&quot;</li></ul><li>difference between inproPitch and GoldPitch</li></ul><li>infrastructure</li><ul><li>Verdengelung of data independent of turns (thus we can still change the notion of turn)<br /></li><li>identification via dialogID/wordID for syntax and dialogID/channel/time for acoustics</li><li>master table has mapping between the two<br /></li></ul></ul></ul>]]></description>
        </item>    </channel></rss>