<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 12pt;
font-family:Calibri
}
--></style></head>
<body class='hmmessage'><div dir='ltr'><div><b>WORKSHOP on Natural Language Processing and Linked Open Data (NLP&LOD)</b></div><div>(http://www.bultreebank.org/NLP&LOD/)</div><div><br></div><div>Collocated with RANLP 2013 (http://www.lml.bas.bg/ranlp2013/)</div><div><br></div><div>12 September 2013</div><div><br></div><div>Hissar, Bulgaria</div><div><br></div><div>============================================================================</div><div><br></div><div><b>DESCRIPTION</b></div><div><br></div><div>In the last decade, the mainstream research in Natural Language Processing</div><div>(NLP) both - in academic and industrial contexts - has focused primarily </div><div>on statistical approaches, which have proved</div><div>very competitive in view of textual data becoming vast in quantity,</div><div>web-based in availability, highly semantic in representation, and dynamic in</div><div>nature.</div><div><br></div><div>A somewhat less mainstream but still quite visible trend has focused on</div><div>knowledge-rich approaches for NLP; this trend has typically complemented</div><div>statistical approaches. Examples include using domain knowledge to enhance</div><div>learning for high-quality automatic NLP in a given domain, adaptation of</div><div>statistical modules to knowledge-rich structures, and hybrid mechanisms for</div><div>language analysis and generation.</div><div><br></div><div>The Linked Open Data (LOD), understood as published structured data, which</div><div>is interlinked and which builds upon standard Web technologies, such as HTTP</div><div>and URIs, as well as on RDF-presented world facts datasets in various</div><div>domains, has become a necessary component within all modern NLP-related</div><div>tasks and applications since it provides large quantities of useful</div><div>knowledge about people, facts, organizations, events, etc.</div><div><br></div><div>In a long-term development, we might expect that richer world knowledge</div><div>would be available even beyond the current Linked Open Data (LOD) with</div><div>respect to larger structured and interconnected data. This would include</div><div>semantics that are richer in world facts and dynamic conceptual knowledge,</div><div>on the one hand. On the other hand, the trends in NLP tools development show</div><div>a strong movement from knowledge-poor towards knowledge-rich and hybrid</div><div>language processing using deep grammars, deep language resources and</div><div>handling big knowledge bases, such as DBPedia, FreeBase, GeoNames, FOAF, etc.</div><div><br></div><div>In this workshop, we build on the complementarity of the two pillars of</div><div>Natural Language Processing — symbolic and probabilistic, further</div><div>reinforced by exploring the recent advances in the area of Linked Open Data</div><div>(LOD). Many contemporary applications rely on the mapping of big amounts of</div><div>texts to world fact databases and ontologies. They also rely on explicating</div><div>the various important relations among entities and events depending on the</div><div>specific task and domain for research and industrial usage. Last, but not</div><div>least, there exist semantic repositories and management systems, such as</div><div>OWLIM (http://www.ontotext.com/owlim), that are highly scalable and support</div><div>inference within big data.</div><div><br></div><div>The workshop aims at gathering NLP researchers and developers, interested in</div><div>hybrid NLP methods and enhancing its connections to LOD.</div><div><br></div><div><br></div><div>============================================================================</div><div><br></div><div><b>TOPICS OF INTEREST</b></div><div><br></div><div>- NLP processing for LOD</div><div>- enhancing NLP applications with LOD</div><div>- information extraction from LOD using NLP techniques</div><div>- manipulating LOD (cleaning, adding information, deleting information, reconstructing facts) with NLP techniques</div><div>- LOD as a corpus</div><div>- mapping LOD to common sense ontologies and language data</div><div>- storing LOD in RDF bases</div><div>- methodological and theoretical approaches to LOD</div><div>- case studies and/or real applications, based on LOD in NLP</div><div>- other issues involving NLP and LOD</div><div><br></div><div><br></div><div>============================================================================</div><div><br></div><div><b>IMPORTANT DATES</b></div><div><br></div><div>Submission deadline: <b>15 July 2013</b> (EXTENDED!)</div><div>Notification of acceptance: 7 August 2013</div><div>Camera-ready copies due: 22 August 2013</div><div>Workshop date: 12 September 2013</div><div><br></div><div><br></div><div>============================================================================</div><div><br></div><div><b>SUBMISSION</b></div><div><br></div><div>Multiple submission policy: We welcome papers that are under review for</div><div>other venues, but, in the event of multiple acceptances, authors are</div><div>requested to notify us and choose which meeting to present and publish the</div><div>work at as soon as possible - we cannot accept for publication or</div><div>presentation work that will be (or has been) published elsewhere.</div><div><br></div><div>Reviewing: Reviewing will be blind. No information identifying the authors</div><div>should be in the paper: this includes not only the authors' names and</div><div>affiliations, but also self-references that reveal authors' identities; for</div><div>example, "We have previously shown (Smith 1999)" should be changed to "Smith</div><div>(1999) has previously shown".</div><div><br></div><div>Paper length and presentation: We invite long (8)+(2 for references) and short (4)+(2 for references) papers.</div><div>Accepted short papers will be presented either as short oral presentations</div><div>or as posters.</div><div><br></div><div>Submission format: Authors should follow the RANLP'2013 submission format.</div><div>The submissions should be uploaded via START system: https://www.softconf.com/ranlp13/NLP_LOD/user/scmd.cgi?scmd=submitPaperCustom&pageid=0</div><div><br></div><div>============================================================================</div><div><br></div><div><b>INVITED SPEAKERS</b></div><div><br></div><div>Christian Chiarcos, Goethe-Universität Frankfurt am Main, Germany</div><div>Borislav Popov, Ontotext AD, Bulgaria</div><div><br></div><div>============================================================================</div><div><br></div><div><b>ORGANIZERS</b></div><div><br></div><div>Petya Osenova, Sofia University, Bulgaria</div><div>Kiril Simov, Bulgarian Academy of Sciences, Bulgaria</div><div>Georgi Georgiev, OntoText Lab, Bulgaria</div><div>Preslav Nakov, Qatar Computing Research Institute, Qatar Foundation, Qatar</div><div><br></div><div><br></div><div>============================================================================</div><div><br></div><div><b>PROGRAMME COMMITTEE</b></div><div><br></div><div>Eneko Agirre, University of the Basque Country, Spain</div><div>Isabelle Augenstein, Sheffield University, UK</div><div>Guido Boella, Università di Torino, Italy</div><div>Kalina Boncheva, Sheffield University, UK</div><div>António Branco, University of Lisbon, Portugal</div><div>Nicoletta Calzolari, Istituto di Linguistica Computazionale, Italy</div><div>Thierry Declerck, DFKI, Germany</div><div>Georgi Dimitroff, Germany</div><div>Kuzman Ganchev, Google, the USA</div><div>Valia Kordoni, Humboldt University in Berlin, Germany</div><div>Jarred McGinnis, King's College London, UK</div><div>Pavel Mihajlov, Ontotext AD, Bulgaria</div><div>Maciej Piasecki, Wroclaw University of Technology, Poland</div><div>Laura Tolosi, Ontotext AD, Bulgaria</div><div>Gertjan van Noord, University of Groningen, the Netherlands</div><div>Piek Vossen, Vrije Universiteit Amsterdam, The Netherlands</div><div><br></div><div><br></div><div><br></div><div><br></div> </div></body>
</html>