Natural Language Processing for Metadata Extraction (NLP4ME 2006)

Workshop to be held on September 12th as part of the

AIMSA 2006 Conference, Varna, September 13-15, 2006


Workshop Programme

Workshop Registration

Travel Information

Guidelines for Authors


Workshop Motivation and Aims

In spite of the massive amount of work in the last years in the area of Semantic Web, the problem of the creation of semantically annotated electronic content is still one of the main bottlenecks for the Semantic Web technology. A key technology, which is employed to overcome this problem is Natural Language Processing, because most of the content of the web is still textual. Any support for automatic and semi-automatic extraction, elicitation of metadata to such content will be of great assistance to the authors and users of the web content.

The workshop aims at being a forum for researchers to present their work in the area of semantic annotation, key word extraction, practical compositional semantics etc. It will provide an opportunity to present and discuss original methods for identification of metadata in text, semantic annotation of text, dealing with multilingual content, interconnecting metadata with ontologies, etc.

Topics of interest:

  • extraction of metadata from texts
  • metadata and ontologies
  • extraction of concepts and keyphrases from text
  • metadata in a multilingual environment
  • metadata in WWW
  • role of linguistic metadata in document processing
  • harmonization of metadata across documents
  • use of metadata in search, retrieval and visualization of documents
  • extraction of metadata from multimodal documents (including text, video, images, sounds, graphics)
  • metadata annotation tools
  • standards for metadata

Important Dates

Deadline for workshop abstract submission: 20th May 2006

Notification of acceptance: 24th June 2006

Final version of paper: 30th July 2006

Workshop: 12th September 2006

Invited Speaker

Paul Buitelaar, DFKI


Papers should describe existing research connected to the topics of the workshop. The presentation at the workshop will be 30 minutes long (25 minutes for presentation and 5 minutes for questions and discussion). Each submission should show: title; author(s); affiliation(s); and contact author’s e-mail address, postal address, telephone and fax numbers. Abstracts (maximum 1500 words, plain-text format) should be sent to:

Petya Osenova

We encourage also demonstration of tools. Please, specify in the abstract if you would like to present your system.

Program Committee

António Branco (Lisbon)
Gosse Bouma (Groningen)
Dan Cristea (Iasi)
Walter von Hahn (Hamburg)
Hamish Cunningham (Sheffield)
Erhard Hinrichs (Tübingen)
Susanne Jekat (Zürich)
Alexander Killing (Zürich)
Atanas Kiryakov (Sofia)
Vladislav Kubon (Prague)
Matthias Kunkel (Koeln)
Lothar Lemnitzer (Tübingen)
Paola Monachesi (Utrecht)
Petya Osenova (Sofia)
Adam Przepiórkowski (Warsaw)
Anne de Roeck (London)
Mike Rosner (Msida, Malta)
Kiril Simov (Sofia)
Tamás Váradi (Budapest)
Cristina Vertan (Hamburg)

Organizing Committee

Kiril Simov
Linguistic Modelling Laboratory, IPP
Bulgarian Academy of Sciences

Paola Monachesi
Utrecht Institute of Linguistics – OTS
Utrecht University
The Netherlands

Lothar Lemnitzer
Seminar für Sprachwissenschaft

Local Organizing Committee

Kiril Simov
Linguistic Modelling Laboratory, IPP,
Bulgarian Academy of Sciences

Petya Osenova
Linguistic Modelling Laboratory, IPP,
Bulgarian Academy of Sciences


The workshop is organized within the EU project LT4eL.

Workshop Web Page

Conference Web Page