Corpora: CFP (Extended): PKDD'2000 Workshop "MACHINE LEARNING AND TEXTUAL INFORMATION ACCESS"

From: Hugo Zaragoza (Hugo.Zaragoza@lip6.fr)
Date: Wed Jun 21 2000 - 17:06:52 MET DST

  • Next message: Roberta Catizone: "Corpora: DRH2000"

          2nd Call for Papers
          EXTENDED SUBMISSION DEADLINE : 10th of July 2000.

          ===============================================
          PKDD'2000 Workshop :
          ===============================================
          MACHINE LEARNING AND TEXTUAL INFORMATION ACCESS
          ===============================================

          September 12, 2000.
          Lyon, France.

          
          Preceding the Fourth European Conference on Principles and
          Practices of Knowledge Discovery in Databases (PKDD'2000).
         
          PKDD'200 : http://eric.univ-lyon2.fr/~pkdd2000/
          WORKSHOP : http://www-connex.lip6.fr/mltia2000.htlm

      

          ===============
          CALL FOR PAPERS
          ===============
          

    DESCRIPTION:
    ------------

    Until recently, the exploitation of large textual collections was
    mainly limited to sorting and retrieving documents. On the other
    hand, systems capable of extracting meaningful document fragments
    dealt only with small domain dependent tasks and models.

    On-line information is becoming widely available and utilized, and
    demand for tools capable of harnessing this information increases
    rapidly. As this information is inherently structured and complex,
    classic models are insufficient. New technological challenges arise,
    the solution of which require the cooperation of several research
    domains.

    By the term "Textual Information Access" we denote here an emerging
    interdisciplinary community of researchers from different fields
    sharing an interest on textual data objects, and Machine or
    Statistical Learning techniques to develop automatic text analysis
    systems.

    Among the new important challenges we will mention the need for
    automatically parametrizable systems (since hand-crafted models cannot
    cope with the heterogeneous nature of data and tasks), the exploitation
    of new structure formalisms for documents and collections (e.g. XML),
    the relations between textual and not textual data, and more generally
    the emerging text-mining and web-mining tasks. In order to solve these
    challenges, a combined approach is needed, exploiting technologies from
    different domains.

    TOPICS OF RELEVANCE:
    --------------------

    Textual Information Access models and applications relating to:
      Information Retrieval and Filtering
      Information Extraction
      Multi-media Information Access
      Knowledge Acquisition
      Topic Detection and Tracking
      Text Summarization
    Representation techniques of:
          Textual Information
          Structure
          Semantics
    User-feedback models and applications
    User-modeling models and applications
    Clustering methods and applications
    Large corpus, scalability and performance issues
    Evaluation techniques

    SOLICITED CONTRIBUTIONS
    -----------------------

    Long papers (up to 12 pages), reporting original completed
    research, development activities, original state of the art
    surveys, etc.

    Short papers (from 4 to 6 pages), reporting ongoing research,
    promising new approaches, position papers.

    All papers will be peer reviewed. Accepted papers will presented
    during the Workshop and will appear in the Workshop Proceedings.

    ORGANIZING COMMITTEE
    --------------------

    Jean-Cédric Chappelier, EPFL, Switzerland,
    Robert Gaizauskas, University of Sheffield, UK,
    Patrick Gallinari, LIP6, Université de Paris 6, France,
    Thorsten Joachims, Universitaet Dortmun, Germany,
    Martin Rajman, EPFL, Switzerland,
    Hugo Zaragoza, Université de Paris 6, France (Chairman).

    SUBMISSION
    ----------

    Submissions should include a short abstract (200 words) and
    comply with
    the following format: A4, 1 column, 2.5cm margins, Times New
    Roman
    12point
    font, single spacing. Postscript is preferred but other standard
    formats
    will be accepted (Word, latex, etc.)

    Submissions should be done electronically by e-mail to Hugo
    Zaragoza
    (Hugo.Zaragoza@lip6.fr), indicating in the subject: MLTIA'2000.

    Please notify to us your intention to submit as soon as possible.

    IMPORTANT DATES
    ---------------

    !!! July 10th 2000 : Deadline for electronic submission of all
    papers.
    August 1st 2000 : Notification of acceptance.
    August 15th 2000 : Deadline for electronic submission of
    camera-ready paper.

    Contact Details
    ---------------
    For more information, please contact:
    Hugo Zaragoza
    LIP6, Université Pierre et Marie Curie (Paris 6)
    4, place Jussieu #169
    75252 Paris Cedex 05
    France.
    Tel: 33 1 44 27 74 91
    Fax: 33 1 44 27 70 00
    Email: Hugo.Zaragoza@lip6.fr

    -- 
    Hugo Zaragoza.
                                                              
    Machine Learning Group                   Tel: (33/0) 1 44277491  
    LIP6, Univeristé de Paris 6              Fax: (33/0) 1 44277000
    Paris (France)                            Hugo.Zaragoza@lip6.fr
    			    http://www-poleia.lip6.fr/~zaragoza
    ---------------------------------------------------------------
      LIP6 / UPMC, Boite 169 / 4, pl.Jussieu / 75252 Paris Cedex 05
    ---------------------------------------------------------------
    



    This archive was generated by hypermail 2b29 : Wed Jun 21 2000 - 21:30:33 MET DST