[Corpora-List] CFP: EMNLP-CoNLL 2007 Joint Conference (Prague)

From: Jason Eisner (jason@cs.jhu.edu)
Date: Fri Mar 16 2007 - 17:22:39 MET

  • Next message: avillavicencio@inf.ufrgs.br: "[Corpora-List] ACL Workshop on Cognitive Aspects of Computational Language Acquisition -- 2nd CFP"

                       Second and Final Call for Papers
     
                               EMNLP-CoNLL 2007
        Conference on Empirical Methods in Natural Language Processing
            Conference on Computational Natural Language Learning

                              June 28-30, 2007
                            Prague, Czech Republic

                      http://cs.jhu.edu/EMNLP-CoNLL-2007

    The annual EMNLP and CoNLL conferences will be holding an unprecedented
    3-day joint meeting this year. The joint conference will be
    co-located with ACL 2007 in Prague. We hereby invite submissions.

    The focus of EMNLP-CoNLL 2007 is learned models and data-driven
    systems concerning all aspects of human language. Both empirical and
    theoretical results are welcome.

    EMNLP is the annual conference organized by SIGDAT, the ACL Special
    Interest Group on linguistic data and corpus-based approaches to NLP.
    Previous EMNLP meetings were held in Sydney (2006), Vancouver (2005),
    Barcelona (2004), Sapporo (2003), Philadelphia (2002), Pittsburgh
    (2001), Hong Kong (2000), College Park (1999), Granada (1998),
    Providence (1997), and Philadelphia (1996).

    CoNLL is the annual conference organized by SIGNLL, the ACL Special
    Interest Group on natural language learning. Previous CoNLL meetings
    were held in New York (2006), Ann Arbor (2005), Boston (2004),
    Edmonton (2003), Taipei (2002), Toulouse (2001), Lisbon (2000), Bergen
    (1999), Sydney (1998), and Madrid (1997).

    TOPICS

    We solicit high-quality papers from academia, government, and industry
    on all areas of interest to SIGDAT and SIGNLL researchers. These areas
    include (among others):

    * Empirical, statistical, or learning approaches to core NLP tasks

      - Words (speech, phonology, morphology, tagging, word senses, ...)
      - Syntax (chunking, entity recognition, parsing, ...)
      - Semantics (information extraction, relation extraction, textual
            entailment, sentiment analysis, full semantics, ...)
      - Generation (machine translation, dialogue, summarization,
            speech synthesis ...)

    * Data-driven techniques in applications of human language technology

      - Information retrieval; information navigation
      - User interfaces, including dialogue systems
      - Domain-specific applications (email, medicine, education, helpdesk, ...)

    * Data mining on natural language data

      - Knowledge discovery
      - Clustering, segmentation, sense discovery, topic discovery,
           dimensionality reduction
      - Language acquisition (grammar induction, etc.)
      - Scalable algorithms on extremely large corpora

    * New machine learning techniques as applied to natural language data

      - Symbolic methods; statistical methods; ensemble methods
      - Architectures for structural and relational learning
      - Learning with little supervision (unsupervised or semi-supervised
            learning, active learning, inductive biases, ...)
      - Techniques for multilinguality or cross-domain adaptation
      - Joint modeling of language and non-language data (networks,
            images, structured databases, ...)
      - Theoretical or empirical comparisons of learning techniques
      - Theory (error bounds, learnability, computational complexity, ...)
      - Algorithms and efficiency

    * Computational models of human language learning

      - Human language acquisition
      - Linguistically informed models, priors, or learning methods
      - Models of analogical or generative processes
      - Learning or frequency effects in human language processing
      - Evolution of language

    SHARED TASK

    CoNLL traditionally runs a friendly competition, the "shared task."
    The 2007 CoNLL shared task is dependency parsing, for the second year
    running. There are actually two tasks: a "multilingual track" as in
    2006, and a new "domain adaptation track" for adapting to different
    domains of English.

    A separate call is being sent out for the shared task. Participants
    must register by JANUARY 20, 2007 [revised to JANUARY 26
    because of an email problem]. The systems and their results
    will be described in short papers, which will be refereed separately
    and will be presented in a special session at EMNLP-CoNLL 2007.

    More information, including the call for participation, is available
    at the shared task website
       http://depparse.uvt.nl/depparse-wiki/SharedTaskWebsite .
    Questions can be sent to conll07st at uvt dot nl.

    SUBMISSIONS

    * FORMAT: Please submit your complete paper as a PDF file.
      Submissions should follow the two-column format of ACL proceedings
      and should not exceed 8 pages, including figures. We strongly
      recommend using the ACL 2007 style files at
      http://ufal.mff.cuni.cz/acl2007/styles/ . If you cannot use these
      style files directly, please read the sample document at that URL
      for a description of the required format. We reserve the right to
      reject submissions that do not conform to this format; note
      especially the restriction to 8 pages at 11-point font.

    * NEW LENGTH POLICY: To encourage thorough citation of related work,
      the References section DOES NOT count against the 8-page submission
      limit for EMNLP-CoNLL 2007. Thus, your PDF file may exceed 8 pages.
      However, all material other than the bibliography must fall within
      the first 8 pages!

    * ANONYMIZATION: As reviewing will be double-blind, the paper should
      not include the authors' names and affiliations. Furthermore, avoid
      self-references that reveal the authors' identities, e.g., "We
      previously showed (Smith, 1991) ..." Instead, use citations such as
      "Smith previously showed (Smith, 1991)...". Papers that do not
      conform to these requirements will be rejected without review.

    * DOUBLE SUBMISSION POLICY: Papers presented at EMNLP-CoNLL should
      consist mainly of new material that has not been previously published.
      Submission of similar papers to EMNLP-CoNLL and another conference
      or workshop must be disclosed on the first page of the submission.
      For details, see the standard policy for ACL-affiliated conferences,
      http://www.cis.udel.edu/~carberry/ACL/double-submission-policy.html .

    * ELECTRONIC SUBMISSION: To submit your paper, please visit
      http://www.softconf.com/acl07/EMNLP-CoNLL07/submit.html , fill in
      the online submission form, and upload your anonymous PDF file.
      The only accepted file format is PDF. You may revise your
      submission up until the deadline given below. Papers submitted
      after the deadline will not be reviewed.

    REVIEWING

    Reviewing will be conducted by an international program committee with
    a number of Area Chairs. Each paper will be blind-reviewed by at
    least 3 program committee members, who can then discuss the paper
    further to resolve disagreements.

    Authors are encouraged to study the actual review form for guidance:
    http://cs.jhu.edu/EMNLP-CoNLL-2007/review-form.html . Reviewers will
    be asked to provide detailed comments, and to score the submitted
    paper on a number of factors such as

    - technical soundness and completeness
    - originality of the problems or solutions
    - experimental and theoretical comparison with previous work
    - clarity of presentation
    - significance to the EMNLP-CoNLL research community

    as well as a new factor, which encourages authors to release their
    systems so that others can replicate or build on their results:

    - likely impact of any promised new resources to be released
        along with the paper (code, data, ...)

    The program committee will make an Best Paper Award to the authors of
    the submission that makes the most original or significant impact on
    the field. We seek to honor scientific contributions that advance the
    state of the field.

    CONFERENCE FORMAT

    The majority of the accepted papers will be presented as 20-minute
    talks, probably in 2 parallel sessions. Additional papers will be
    accepted for presentation in poster sessions. We also plan additional
    events such as invited talks.

    ORGANIZERS

    Program Chairs:

       Jason Eisner (Johns Hopkins University)
       Taku Kudo (Google Japan)

    Area Chairs:

       David Chiang (USC Information Sciences Institute)
       Alexander Clark (Royal Holloway University of London)
       Michael Collins (Massachusetts Institute of Technology)
       Hal Daume III (University of Utah)
       Sanjeev Khudanpur (Johns Hopkins University)
       Katrin Kirchhoff (University of Washington)
       Dekang Lin (Google Inc.)
       David McAllester (Toyota Technological Institute - Chicago)
       Manabu Okumura (Tokyo Institute of Technology)
       Anoop Sarkar (Simon Fraser University)
       Suzanne Stevenson (University of Toronto)
       Carlo Strapparava (Istituto Trentino di Cultura)
       Hans Uszkoreit (Saarland University DFKI)
       Menno van Zaanen (Macquarie University)
       Marilyn Walker (University of Sheffield)
       Janyce Wiebe (University of Pittsburgh)

    Shared Task Organizer:

       Joakim Nivre (Vaxjo University)

    Local Arrangements Chair:

       Jan Hajic (Charles University)

    IMPORTANT DATES

    Paper submission deadline: Mon, March 26, 2007, 11:59pm EDT (GMT -0400)
    Notification of acceptance: Thu, April 26, 2007
    Camera-ready copy due: Mon, May 14, 2007
    Conference meeting: Thu, June 28 - Sat, June 30, 2007

    NEWS AND CONTACT INFORMATION

    Updates will be posted at the conference home page:
       http://cs.jhu.edu/EMNLP-CoNLL-2007

    Questions may be sent to the program chairs at this address:
       emnlp-conll-2007 at clsp dot jhu dot edu



    This archive was generated by hypermail 2b29 : Fri Mar 16 2007 - 18:23:15 MET