EACL 2003 Workshop

Language Technology and the Semantic Web

 

3rd Workshop on NLP and XML (NLPXML-2003)



Endorsed by
OntoWeb SIG5 on Language Technology in Ontology Development and Use

Within the NLP community, XML is accepted as the standard for data representation, especially for purposes of interchange and software interoperability. However, XML and the standards that surround it (XML schemas, XSL and XSLT, etc.) not only provide a standard representation format, but, more abstractly, also define a modeling language that has important ramifications for the ways in which we organize data, annotations, software architecture, etc. In addition, the Resource Definition Framework (RDF) and the Semantic Web define an overall architecture for resources of all kinds whose eventual implications for natural language processing are less well understood within the NLP community.

 

The goal of this workshop is two-fold: (1) to provide a forum for presentation and discussion of the use of XML and related standards (RDF, OWL, etc.) in NLP (including resource and software development, applications, tools, etc.); and (2) to clarify the "big picture" for NLP applications and resources vis a vis the XML framework and development of the Semantic Web. As such, the workshop is intended not only for those already using XML, but also members of the NLP community who seek a fuller understanding of the motivations and implications of XML, the Semantic Web, and related standards for the field.

 

Rather than arguing the overall merits and possibilities of the Semantic Web, the workshop is intended to focus on the more technical aspects of its use and implementation. The workshop will include invited presentations that will cover in some depth the XML/RDF/OWL/Semantic Web architecture and attempt to identify the interactions among various activities (resource creation and annotation, application development, etc.) as well as the potential interactions with the RDF and Semantic Web layers. The number of presented papers will be limited to allow ample time for discussion and comment after each. This format should provide a forum for interaction among members of possibly disparate research communities, and a means for attendees to increase their knowledge and understanding of the complexity of Semantic Web technologies.


This workshop will be the third in a series, following on from the first NLPXML Workshop held at NLPRS 2001 in Tokyo, Japan and the second at COLING 2002 in Taipei, Taiwan. The purpose of the workshop series is to enable communication and cooperative development of XML/Semantic Web practices and standards for language resource creation and use, application development, etc.

 

WOKSHOP TOPICS

 

The workshop is concerned with the following topics:

 

WORKSHOP PROGRAM
Sunday, April 13

9:00-9:15 Welcome
9:15-10:00

Setting the Context: The Relevance of the Semantic Web for Language Technology
Nancy Ide and Paul Buitelaar

10:00-10:30 Semantic Web Enabled, Open Source Language Technology
Kalina Bontcheva, Atanas Kiryakov, Hamish Cunningham, Borislav Popov and Marin Dimitrov
10:00-10:30 Break
11:00-11:30 A Multi-Layered, XML-Based Approach to the Integration of Linguistic and Semantic Annotations
Paul Buitelaar, Thierry Declerck, Bogdan Sacaleanu, Spela Vintar, Diana Raileanu and Claudia Crispi
11:30-12:00 The NITE Object Model Library for Handling Structured Linguistic Annotation on Multimodal Data Sets
Jean Carletta, Jonathan Kilgour, Tim O’Donnell, Stefan Evert and Holger Voormann
12:00-12:30 OntoTag: XML / RDF(S) / OWL Semantic Web Page Annotation in ContentWeb
Guadalupe Aguado de Cea, Inmaculada Alvarez-de-Mon, Asuncion Gomez-Perez and
Antonio Pareja-Lora
12:30-2:00 Lunch
2:00-2:30 Enhancing XCES to xComForT : An Extensible Modular Architecture for the Annotation and
Manipulation of Text Resources
Marion Freese, Ulrich Heid and Martin Emele
2:30-3:00 Cross Document Annotation for Multimedia Retrieval
Dennis Reidsma, Jan Kuper, Thierry Declerck, Horacio Saggion and Hamish Cunningham
3:00-3:30 Lexical Databases in XML
Pavel Smrz and Martin Povolny
3:30-4:00 Break
4:00-4:30 Linguistic Parsing of Lists in Structured Documents
Salah Ait-Mokhtar, Veronika Lux and Eva Banik
4:30-6:00 Panel and Discussion


REGISTRATION INFORMATION

 

To register for the workshop and the main EACL conference, please go to the EACL 2003 conference page.

 

 

WORKSHOP CHAIRS

 

Nancy Ide

Vassar College, USA

e-mail : ide@cs.vassar.edu

 

Laurent Romary

LORIA/CNRS, France

e-mail : romary@loria.fr        

 

Graham Wilcock

University of Helsinki, Finland

e-mail: graham.wilcock@helsinki.fi

 

 

PROGRAM COMMITTEE

 

Paul Buitelaar (DFKI, Germany)

Jean Carletta (University of Edinburgh, UK)

Key-Sun Choi (KAIST, Korea)

Hamish Cunningham (University of Sheffield, UK)

Thierry Declerck (DFKI, Germany)

David Durand (Brown University, USA)

Tomaz Erjavec (Institute Jozef Stefan, Slovenia)

Nancy Ide (Vassar College, USA)

Christophe Laprun (NIST, USA)

Ewan Klein (University of Edinburgh, UK)

Jimmy Lin (MIT, USA)

Chieko Nakabasami (Tokyo University, Japan)

Naoyuki Nomura (Justsystem/Hosei University, Japan)

Antonio Pareja-Lora (UCM, Spain)

Laurent Romary (Loria/CNRS, France)

Manfred Stede (U Potsdam, Germany)

Henry Thompson (University of Edinburgh, UK)

Fabio Vitali (University of Bologna, Italy)

Kuansan Wang (Microsoft, USA)

Graham Wilcock (University of Helsinki, Finland)