[Elsnet-list] Second Call for Papers: ACL Workshop on Balto-Slavonic NLP and IE

Ralf Steinberger ralf.steinberger at jrc.it
Fri Mar 2 09:01:56 CET 2007


SECOND CALL  FOR  PAPERS

------------------------

 

Balto-Slavonic Natural Language Processing 2007 (BSNLP 2007)

with Special Theme: Information Extraction and Enabling Technologies

 

June 29, 2007 

Prague, Czech Republic

 

http://langtech.jrc.it/BSNLP2007

 

BSNLP will be held in conjunction with the ACL 2007 conference
(http://ufal.mff.cuni.cz/acl2007/)

and is co-organised by the European Commission's Joint Research Centre.

 

TOPIC AND MOTIVATION:

 

The recent political and economic changes in Central and Eastern Europe 

and the related on-going enlargement of the European Union brings into focus
new 

cultures and languages. Among them, the languages from the Balto-Slavonic

group have an outstanding role because of their rich cultural heritage and
the

widespread use - over 400 million speakers.

 

The topic of the workshop addresses Natural Language Processing (NLP) for
the 

Balto-Slavonic languages, with the focus on Information Extraction (IE) and 

enabling technologies for this language family. The task of IE is to
identify a 

predefined set of concepts from natural language text. The spectrum of IE 

tasks ranges from named-entity recognition, through relation extraction and 

co-reference resolution to the identification of complex events and 

cross-document entity profile extraction. Although a considerable 

amount of IE-related work exists, most of the studies are concentrated on a

few major languages. Research on this topic, as well as on general-purpose
NLP 

tools in the context of Balto-Slavonic languages, is still in its early
stage and is

progressing relatively slowly. Due to some specific  phenomena like the
highly inflectional 

character and relatively free word order, a construction of IE systems and
other 

language processing tools (question-answering, text summarization, machine
translation) 

for these languages is an intriguing and challenging task.

 

This workshop can be seen as the follow-up to the successful workshop on 

Information Extraction for Slavonic and Other Central and Eastern European 

Languages (http://lml.bas.bg/IESL2003) held in conjunction with the RANLP
2003 

conference. It is also related to the EACL 2003 workshop on Morphological 

Processing of Slavic Languages (http://nl.ijs.si/mpsl03). In particular, we
would 

strongly encourage submissions describing systems, resources or solutions
that 

are made available to the wider public, as these would help to promote 

computational linguistics applications for these languages.

 

AREAS OF INTEREST include, but are not limited to:

 

A. Specific challenges for Balto-Slavonic NLP, in particular in the context
of IE

and underlying technologies

 

- text segmentation

- morphological analysis

- morphology models

- morpho-syntactic disambiguation

- named-entity recognition 

- named-entity disambiguation (e.g., geo-referencing)

- named-entity lemmatisation

- term and keyword extraction

- name variant recognition and merging

- syntactic parsing and chunking

- co-reference resolution

- word sense disambiguation

- corpus-based knowledge acquisition

 

B. Multilingual IE frameworks and techniques applied to these languages

 

- tools and resources (freely available for research purposes will be
preferred)

- experience with, and evaluation of, linguistic data and processing
resources

- comparative evaluation between languages

 

C. IE solutions for these languages:

 

- scenario template filling / event extraction

- relation extraction

- automatic pattern learning

- corpus studies and statistical techniques for IE

- IE from Web sources

- IE-based ontology population

- IE evaluation

- IE techniques for Question/Answering and Answer Extraction

- Utilisation of IE-based techniques in other NLP applications

 

INTENDED AUDIENCE

 

The goal of this workshop is to bring together researchers and practitioners

working on NLP for Balto-Slavonic languages, in particular on IE and core 

technologies supporting IE for these languages. The workshop will 

give an opportunity to exchange ideas and experience, to discuss 

hard-to-tackle problems in this field of research, and to make available 

resources more widely known.

 

SUBMISSION

 

Papers should describe original work and should indicate the state of 

completion of the reported results. In particular, an overlap with
previously 

published work should be clearly mentioned. Submissions will be 

judged on correctness, novelty, technical strength, clarity of presentation,

usability, and significance/relevance to the workshop. 

 

Submissions should follow the two-column format of the ACL 2007 

main-conference proceedings and should not exceed eight (8) pages, 

including references. We recommend to use either the LaTeX style file 

or the Microsoft-Word style file, which can be found at
http://ufal.mff.cuni.cz/acl2007/styles.

 

The reviewing will be blind. Therefore, the paper should not include the
authors' 

names and affiliations. Furthermore, self-citations and other references
that could 

reveal the author's identity should be avoided. 

 

Submission will be electronic. The only accepted format for submitted papers


is Adobe PDF. Papers must be submitted no later than April 1, 2006

using the submission webpage http://langtech.jrc.it/BSNLP2007/submission.

 

Submissions will be reviewed by 3 members of the Program Committee. 

Authors of accepted papers will receive guidelines regarding how to produce 

camera-ready versions of their papers for inclusion in the ACL workshop 

proceedings.

 

IMPORTANT DATES

 

Workshop Paper Submission deadline: April 1

Notification of Acceptance: April 25

Camera-ready Version: May 9

Workshop: June 29, 2007.

 

LOCATION

 

Prague, the capital of the Czech Republic, is located in the centre of
Europe. It

is one of the most valuable historical city reserves in Europe. The
historical core 

of the city is listed in the UNESCO World Cultural and Natural Heritage
Register. 

The workshop itself will take place in the TOP HOTEL Praha, located in the
quiet 

neighbourhood of the Prague 4 district, only 15-20 minutes from the historic
centre 

of Prague. 

 

Prague is easily reachable by car, bus or train from Central Europe (only
3-hour 

drive from Vienna or Budapest or 4 hours from Berlin or Munich), by cheap
flights 

from the rest of Europe, and by several direct flights from overseas. 

 

FURTHER INFORMATION

 

For further information please write to bsnlp2007 at jrc.it

or check the workshop web page http://langtech.jrc.it/BSNLP2007.

 

PROGRAM COMMITTEE

 

Tania Avgustinova (University of Saarland / DFKI, Germany)

Kalina Bontcheva (University of Sheffield, UK)

Tomaz Erjavec (Jozef Stefan Institute, Slovenia)

Vaclav Kubon (Charles University Prague, Czech Republic)

Anna Kupsc (Loria, France)

Ruta Marcinkeviciene (Vytautas Magnus University, Kaunas, Lithuania)

Agnieszka Mykowiecka (Polish Academy of Sciences, Poland)

Jakub Piskorski (Joint Research Centre, Italy)

Bruno Pouliquen (Joint Research Centre, Italy)

Hristo Tanev (Joint Research Centre, Italy)

Marko Tadic (University of Zagreb, Croatia)

Agata Savary (University of Tours, France)

Kiril Simov (Bulgarian Academy of Sciences, Bulgaria)

Wojciech Skut (Google Inc., USA)

Ralf Steinberger (Joint Research Centre, Italy)

Dusko Vitas (University of Beograd, Serbia)

Roman Yangarber (University of Helsinki, Finland) 

 

PROGRAM COMMITTEE CHAIR

 

Jakub Piskorski (Joint Research Centre, Italy)

Hristo Tanev (Joint Research Centre, Italy)

 

ORGANIZING COMMITTEE

 

Jakub Piskorski (Joint Research Centre, Italy)

Bruno Pouliquen (Joint Research Centre, Italy)

Hristo Tanev (Joint Research Centre, Italy)

Ralf Steinberger (Joint Research Centre, Italy)

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://stratus.let.uu.nl/pipermail/elsnet-list/attachments/20070302/0381e793/attachment.html


More information about the Elsnet-list mailing list