Call for papers

WORKSHOP GOALS

The workshop will focus on Information Extraction (IE) for Slavonic and other Central and Eastern European languages. Information Extraction is the process of deriving quantifiable, unambiguous data from natural language text or speech. Various types of data may be extracted, from simple entity identification, through entity reference resolution and descriptive modifier attachment, to the identification of complex events and relations.

TOPICS include but are not limited to:

• unique challenges for IE in these languages
• architectures and development environments for IE in these languages
• portability of existing IE tools for other languages
• named entity recognition
• relation extraction
• template filling and scenario templates
• corpus studies and statistical techniques for IE in these languages
• linguistic aspects of IE for these languages
• evaluation of IE for these languages

INTENDED AUDIENCE

This workshop aims at bringing together researchers working on Information Extraction for Slavonic and other Central and Eastern European languages in EU and the candidate countries. There is now a growing body of research in this area and this workshop aims to provide a forum for these researchers to exchange insight and discuss problems. This will also give an opportunity to push further the discussion on portability of information extraction tools across languages.

PC CHAIR

PROGRAMME COMMITTEE

SUBMISSION

Submissions should be A4, two-column format and should not exceed seven pages (poster and demo submissions should be no longer than 5 pages), including cover page, figures, tables and references. Times New Roman 12 font is preferred. The first page should state the title of the paper, the author's name(s), affiliation, surface and email address(es), followed by keywords and an abstract and continue with the first section of your paper. Papers should be submitted electronically in **PDF** or as **MS-Word** and **PS** files. In exceptional circumstances hard copies may be accepted.

Send your electronic submission to iesl03@lml.bas.bg with a copy to hellen@lml.bas.bg

Submissions will be reviewed by 3 members of the Programme Committee. Authors of accepted papers will receive guidelines regarding how to produce camera-ready versions of their papers for inclusion in the proceedings. Guidelines for producing camera-ready versions and Demo text can be found at the RANLP conference web site: http://www.lml.bas.bg/ranlp2003.

IMPORTANT DEADLINES

LOCATION

The picturesque resort of Borovets is located in the Rila mountains and is one of the most famous winter resorts in South-East Europe, a frequent meeting place for the elite in world skiing. The resort is 1350 m above sea level, at the foot of peak Moussala (2925 m) - the highest on the Balkan Peninsula. The resort of Borovets is 73 km from Sofia and 126 km from Plovdiv (see the map at the conference site), which means that both Sofia and Plovdiv with their international airports can serve as arrival/departure points. In addition to regular public transport, the organisers will provide daily shuttle buses from Sofia airport to the conference location at an inexpensive rate. A taxi from Sofia to Borovets is relatively cheap, so it is also possible to take a taxi from the international airport in Sofia to the workshop venue.

FURTHER INFORMATION

Further information can be obtained from Elena Paskaleva hellen@lml.bas.bg and iesl03@lml.bas.bg

ORGANIZERS and SPONSORS

The main local organizer is the Linguistic Modeling Department, Central Laboratory for Parallel Processing, Bulgarian Academy of Sciences (www.lml.bas.bg). IESL-2003 is supported by the European Commission under contract ICA1-2000-70016 "BIS-21 Centre of Excellence".

Partial support for attending the workshop would be provided especially for authors of accepted papers, who work permanently in the associated countries, in West Balkans and New Independent States.

THE TEAM BEHIND IESL-03