<?xml version='1.0'?><rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:georss="http://www.georss.org/georss" >
<channel>
	<title><![CDATA[MultiLing Community Site: MultiLing 2013 - Call for Contributors]]></title>
	<link>http://multiling.iit.demokritos.gr/pages/view/668/multiling-2013-call-for-contributors</link>
	<description><![CDATA[]]></description>
	
	<item>
	<guid isPermaLink="true">http://multiling.iit.demokritos.gr/pages/view/668/multiling-2013-call-for-contributors</guid>
	<pubDate>Sat, 09 Feb 2013 16:42:35 +0200</pubDate>
	<link>http://multiling.iit.demokritos.gr/pages/view/668/multiling-2013-call-for-contributors</link>
	<title><![CDATA[MultiLing 2013 - Call for Contributors]]></title>
	<description><![CDATA[<p>Call for Data Contributors - MultiLing 2013<br /> (Please <strong>feel free to forward this message</strong>. Apologies for cross-postings.)<br /> <br /> Overview<br /> =======<br /> MultiLing 2013 is a workshop, held within ACL 2013, which covers three subdomains of <br /> Natural Language Processing, focused on the multilingual aspect of summarization. <br /> The MultiLing 2013 workshop builds upon the Text Analysis Conference (TAC) <br /> MultiLing Pilot task of 2011, where systems were asked to generate fluent, representative <br /> summaries (around 250 words) for each of 10 predefined topics per language. <br /> Each topic was described by10 source documents. <br /> The set of documents was in one of the following&nbsp; 7 languages: Arabic, Czech, English, <br /> French, Greek, Hebrew and Hindi. <br /> Based on the challenges revealed in MultiLing 2011, this year we also address the problems <br /> of multilingual summary evaluation and data collection. This call asks for contributors for <br /> the data collection process.<br /> <br /> <strong>Workshop</strong><strong> URL</strong>: http://multiling.iit.demokritos.gr/pages/view/662/multiling-2013<br /> <br /> Scope of the workshop:<br /> ================<br /> - Multilingual Summarization <br /> - Multilingual Summarization Evaluation <br /> - Multilingual Summarization Data Collection and Exploitation <br /> The workshop will be based on a multilingual summarization task, as in the original MultiLing Pilot, <br /> adding an evaluation task and presentations related to Data Collection and Exploitation. <br /> <br /> Call for Contributors:<br /> ==============<br /> This call requests your support and help as <strong>Contributors</strong>. The Contributors are meant to<br /> help <strong>co-ordinate and realize the MultiLing data collection for different languages</strong>. <br /> The data collection process involves <strong>translation across languages</strong> (from English to a selected<br /> language) of news texts (from the WikiNews site, most probably), the <strong>generation of human <br /> summaries</strong> in each language, as well as the <strong>evaluation of summaries</strong> (from humans and/or systems). <br /> Each Contributor is expected to undertake a single language.&nbsp; <br /> For <strong> details</strong> on the required effort see the section <strong>"Details concerning the effort"</strong> later in this document.<br /> <br /> The Contributors are expected to <strong>co-author an overview paper</strong>, summarizing the data collection effort <br /> for their language&nbsp; and the lessons learned. The paper will be reviewed, improved and submitted as part <br /> of the <strong>ACL MultiLing 2013 Workshop proceedings</strong>.&nbsp; If the overview paper ends up being too long,<br /> there may be several overview papers, covering different languages. The Contributors can request a slot in the <br /> "Multilingual Summarization Data Collection and Exploitation" part of the workshop for a <strong>presentation</strong>. <br /> The Contributors will also receive full visibility and will be acknowledged in the MultiLing site and communication.<br /> <br /> How to apply to be a Contributor:<br /> ======================<br /> <strong>Contact George Giannakopoulos via e-mail ( <a href="mailto:ggianna@iit.demokritos.gr">ggianna@iit.demokritos.gr</a> ) describing the language you are<br /> interested in and</strong><strong> providing </strong><strong>your contact information by March 1st, 2013.</strong><strong><br /> </strong><strong> </strong><br /> Details concerning the Contributor effort:<br /> ============================<br /> This <strong>effort</strong> is meant to be <strong>community-based</strong><strong>, thus the cost of gathering data for a single language <br /> will be split among several Contributors, if possible.</strong><br /> <br /> For existing languages (Arabic, Czech, English, French, Greek, Hebrew and Hindi) we mean to increase <br /> the current corpus by 50% (i.e., add 5 more topics). <br /> The <strong>effort in the languages existing in TAC 2011</strong> (<strong>Arabic</strong><strong>, </strong><strong>Czech</strong><strong>, </strong><strong>English</strong><strong>, French, Greek, Hebrew <br /> or Hindi</strong>) will be:<br /> - to check inconsistencies and problems with the existing data (gold summaries, evaluations) and correct them, <br /> - translate 50 new source documents from English to the target language (10 documents per new topic)<br /> - provide 3 human summaries for each of the 5 new topics.<br /> - have 3 judges evaluate each of the automatic summaries that will be submitted (in TAC 2011 we had <br /> 30 to 80 summaries per language, depending on the language).<br /> <br /> The <strong>effort in new languages (e.g., Chinese, Japanese, German, Italian, Spanish, Hungarian, Swedish, Turkish, ...) </strong>will be:<br /> - translate 150 source documents (between&nbsp; from English to the target language (10 documents per topic, for 15 topics)<br /> - provide 3 human summaries for each of 15 new topics.<br /> - have 3 judges evaluate each of the automatic summaries that will be submitted (in TAC 2011 we evaluated 30 to 80 summaries per language, depending on the language).<br /> <br /> The data collection process will start by mid-February and may need to be concluded by mid-April.<br /> <br /> Please <strong>feel free to forward this call</strong>, if you consider that there is someone that will want to help add a new language.<br /> <br /> <br /><br /></p>]]></description>
	<dc:creator>George Giannakopoulos (Admin)</dc:creator>
</item>

</channel>
</rss>