Sponsored by:
 

SIGDAT, the Association for Computational Linguistics' special interest group on linguistic data and corpus-based approaches to NLP, invites submissions to EMNLP 2002. The conference will be held at University of Pennsylvania, Philadelphia, PA, USA on July 6-7, immediately preceding the anniversary 40^th meeting of the ACL (ACL 2002).

We are interested in papers from academia, government, and industry on all areas of traditional interest to the SIGDAT community and aligned fields, including but not limited to:

• information extraction
• information retrieval
• language and dialog modeling
• lexical acquisition
• machine translation
• multilingual technologies
• question answering
• statistical parsing
• summarization
• tagging
• term and named entity extraction
• word sense disambiguation
• word, term, and text segmentation

As a follow-up to last year's focus on analyzing the current "Successes and Challenges" in the corpus-based methods, we encourage submissions on the theme

• using Really Large Corpora (cf. last year's Eric Brill's talk);
• using previously neglected methods, including those from non-NLP fields, such as biology, nuclear physics, or finance, with promising results and/or reasonable potential for the future;
• employing known methods in a radically different way or on problems they were not tried upon previously, with truly significant improvement;
• combining intuition-based and data-based methods (finally!) with substantially improved results on known problems.

• Requirements: Submissions must describe original, completed, unpublished work, and include concrete evaluation results when appropriate. Papers being submitted to other meetings must provide this information (see submission format); in the event of multiple acceptances, authors are requested to immediately notify the EMNLP program chair (hajic@ufal.mff.cuni.cz) and choose which meeting to present and publish the work at as soon as possible - EMNLP cannot accept for publication or presentation work that will be (or has been) published elsewhere.

• Format: Submissions must be electronic only (contrary to last year's EMNLP!), and should consist of full papers of approximately 3200 words (exclusive of references, tables, figures and equations). Authors are strongly encouraged to use the LaTeX style files or MSWord equivalents available here -- these formats will ease the transition to the proceedings version.

  Reviewing will be blind. No information identifying the authors should be in the paper: this includes not only the authors' names and affilations, but also self-references that reveal authors' identities; for example, "We have previously shown (Smith 1999)" should be changed to "Smith (1999) has previously shown". A separate identification page is required: see below.

• Procedure: First, an electronic notice of intent to submit is required. Please email (emnlp02@ufal.mff.cuni.cz) (subject line EMNLP 2002 ITS) by April 4 with the following information:

  Paper title
  Authors' names, affiliations, and email addresses
  Contact author
  A short list of keywords
  A short (no more than 5 lines) summary of the contents
  Whether or not the paper is under consideration for other conferences (please specify)
  

  As a reply to the ITS, a 3-digit ID number will be sent back as an acknowledgement. This number will be important for identification of the submission proper. More detailed instructions will be mailed to you along with the ID; see also below.

  Second, an electronic version of the paper in PostScript format, named <an-ID-number-received-as-a-reply-to-the-IST>.ps, formatted for A4 or a letter-size paper (without identifying information) together with a single text-only ("ASCII") file, named <an-ID-number-received-as-a-reply-to-the-IST>.txt, containing all the information from the notice of intent to submit (i.e., title, authors, contact author, keywords, summary, and multiple-submission information must be received by April 9, 23:00 GMT DST (6pm EDT) at the following address: emnlp02@ufal.mff.cuni.cz. Please use gzip or plain old zip (or PKZIP) for compression to ensure nothing is lost during the email transfer.

  In case of difficulties sending the PostScript version, please generate a PDF format instead (and name it accordingly: <an-ID-number-received-as-a-reply-to-the-IST>.pdf). Let us stress again that the PostScript format is nevertheless strongly preferred.

  Only in case of really, REALLY unsolvable difficulties in sending the electronic version, please send a single hardcopy of the paper and the ID page to

  EMNLP 2002 Submissions
  Jan Hajic
  UFAL - Linguistics
  MFF UK
  Malostranske nam. 25
  CZ-11800 Prague 1
  Czech Republic
  

  The EMNLP committee is not responsible for postal delays or other e-mail and mail problems. Submissions that do not conform to the guidelines above are subject to rejection without review.

Important Dates

• Anoop Sarkar
• Atro Voutilainen
• Thorsten Brants
• Eric Brill
• Chris Brew
• Ciprian Chelba
• Eugene Charniak
• Eric Gaussier
• Erik Tjong Sang Kim
• Gary Geunbae Lee
• Grace Ngai
• Hang Li
• Marti Hearst
• Helen Meng
• Rebecca Hwa
• Ido Dagan
• Hitoshi Iida
• Kentaro Inui
• Jason Eisner
• James Henderson
• John C. Henderson
• Joe Zhou
• Wessel Kraaij
• Ken Church
• Liz Liddy
• Marc Light
• Dekang Lin
• Lillian Lee
• Lluis Marquez
• Mike Collins
• Paola Merlo
• Maria Lapata
• Masaaki Nagata
• Guenter Neumann
• Hwee Tou Ng
• Jian-Yun Nie
• Franz-Josef Och
• Paul Jacobs
• Rada Mihalcea
• Regina Barzilay
• Radu Florian
• Stephen Clark
• Ted Pedersen
• Paola Velardi
• Kevin Knight
• Martha Palmer
• Philip Resnik
• Adam Kilgarriff
• Karel Oliva
• Margaret King

Conference URL