[Elsnet-list] Second CFP: Workshop on NLP&LOD, Bulgaria
petyaosenova at hotmail.com
Tue Jun 18 15:00:58 CEST 2013
= apologies for multiple postings =
WORKSHOP on Natural Language Processing and Linked Open Data (NLP&LOD)(http://www.bultreebank.org/NLP&LOD/)
Collocated with RANLP 2013 (http://www.lml.bas.bg/ranlp2013/)
12/13 September 2013
In the last decade, the mainstream research in Natural Language Processing(NLP) both - in academic and industrial contexts - has focused primarily on statistical approaches, which have provedvery competitive in view of textual data becoming vast in quantity,web-based in availability, highly semantic in representation, and dynamic innature.
A somewhat less mainstream but still quite visible trend has focused onknowledge-rich approaches for NLP; this trend has typically complementedstatistical approaches. Examples include using domain knowledge to enhancelearning for high-quality automatic NLP in a given domain, adaptation ofstatistical modules to knowledge-rich structures, and hybrid mechanisms forlanguage analysis and generation.
The Linked Open Data (LOD), understood as published structured data, whichis interlinked and which builds upon standard Web technologies, such as HTTPand URIs, as well as on RDF-presented world facts datasets in variousdomains, has become a necessary component within all modern NLP-relatedtasks and applications since it provides large quantities of usefulknowledge about people, facts, organizations, events, etc.
In a long-term development, we might expect that richer world knowledgewould be available even beyond the current Linked Open Data (LOD) withrespect to larger structured and interconnected data. This would includesemantics that are richer in world facts and dynamic conceptual knowledge,on the one hand. On the other hand, the trends in NLP tools development showa strong movement from knowledge-poor towards knowledge-rich and hybridlanguage processing using deep grammars, deep language resources andhandling big knowledge bases, such as DBPedia, FreeBase, GeoNames, FOAF, etc.
In this workshop, we build on the complementarity of the two pillars ofNatural Language Processing — symbolic and probabilistic, furtherreinforced by exploring the recent advances in the area of Linked Open Data(LOD). Many contemporary applications rely on the mapping of big amounts oftexts to world fact databases and ontologies. They also rely on explicatingthe various important relations among entities and events depending on thespecific task and domain for research and industrial usage. Last, but notleast, there exist semantic repositories and management systems, such asOWLIM (http://www.ontotext.com/owlim), that are highly scalable and supportinference within big data.
The workshop aims at gathering NLP researchers and developers, interested inhybrid NLP methods and enhancing its connections to LOD.
TOPICS OF INTEREST
- NLP processing for LOD- enhancing NLP applications with LOD- information extraction from LOD using NLP techniques- manipulating LOD (cleaning, adding information, deleting information, reconstructing facts) with NLP techniques- LOD as a corpus- mapping LOD to common sense ontologies and language data- storing LOD in RDF bases- methodological and theoretical approaches to LOD- case studies and/or real applications, based on LOD in NLP- other issues involving NLP and LOD
Submission deadline: 5 July 2013Notification of acceptance: 2 August 2013Camera-ready copies due: 16 August 2013Workshop date: 12/13 September 2013
Multiple submission policy: We welcome papers that are under review forother venues, but, in the event of multiple acceptances, authors arerequested to notify us and choose which meeting to present and publish thework at as soon as possible - we cannot accept for publication orpresentation work that will be (or has been) published elsewhere.
Reviewing: Reviewing will be blind. No information identifying the authorsshould be in the paper: this includes not only the authors' names andaffiliations, but also self-references that reveal authors' identities; forexample, "We have previously shown (Smith 1999)" should be changed to "Smith(1999) has previously shown".
Paper length and presentation: We invite long (8) and short (4) papers.Accepted short papers will be presented either as short oral presentationsor as posters.
Submission format: Authors should follow the RANLP'2013 submission format.
The submissions should be uploaded via START system: https://www.softconf.com/ranlp13/NLP_LOD/user/scmd.cgi?scmd=submitPaperCustom&pageid=0
Invited speakers: TBA
Petya Osenova, Sofia University, BulgariaKiril Simov, Bulgarian Academy of Sciences, BulgariaGeorgi Georgiev, OntoText Lab, BulgariaPreslav Nakov, Qatar Computing Research Institute, Qatar Foundation, Qatar
Eneko Agirre, University of the Basque Country, SpainIsabelle Augenstein, Sheffield University, UKGuido Boella, Università di Torino, ItalyKalina Boncheva, Sheffield University, UKAntónio Branco, University of Lisbon, PortugalNicoletta Calzolari, Istituto di Linguistica Computazionale, ItalyThierry Declerck, DFKI, GermanyGeorgi Dimitroff, GermanyKuzman Ganchev, Google, the USAValia Kordoni, Humboldt University in Berlin, GermanyJarred McGinnis, King's College London, UKPavel Mihajlov, Ontotext AD, BulgariaMaciej Piasecki, Wroclaw University of Technology, PolandLaura Tolosi, Ontotext AD, BulgariaGertjan van Noord, University of Groningen, the NetherlandsPiek Vossen, Vrije Universiteit Amsterdam, The Netherlands
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Elsnet-list