[Corpora-List] Using Corpora for NLG - CALL FOR PARTICIPATION

From: Anja Belz (a.s.belz@itri.brighton.ac.uk)
Date: Wed Jun 15 2005 - 18:12:10 MET DST

  • Next message: Michiel Kamermans: "[Corpora-List] Japanese/English aligned corpora?"

    >>> CALL FOR PARTICIPATION - ALL WELCOME <<<<

    Using Corpora for Natural Language Generation
    =============================================

    Using Corpora for Natural Language Generation is a pre-conference
    workshop at Corpus Linguistics 2005, to be held in Birmingham, on 14
    July 2005.

    The workshop programme combines diverse presentations on the use of
    corpora in NLG, ranging from traditional, manual techniques to the
    more recent machine learning and statistical methods. The goals of the
    workshop are to present and discuss current research, to compare
    manual and automatic corpus exploitation, to evaluate achievements,
    and to identify challenges for the future.

    There will be an invited talk by Irene Langkilde-Geary, one of the
    founding researchers of the field of statistical generation, eight
    technical contributions, a session of brief presentations of specific
    corpora and their possible NLG uses, and a panel discussion on the
    topics of the workshop.

    We would like to encourage wide participation, especially from (but
    not necessarily limited to) researchers in any field related to NLG,
    MT, dialogue, corpus building, and neighbouring disciplines.

    Any workshop participant may contribute a brief corpus presentation.
    Please send the name of your corpus and a one-paragraph description to
    the workshop organisers (ucnlg at itri.brighton.ac.uk).

    We look forward to seeing you in Birmingham on 14th July.

    Registration & Accommodation
    ----------------------------

    Registration is open at the Corpus Linguistics 2005 website
    (http://www.corpus.bham.ac.uk/conference/registrationformCL2005.htm).
    Please note that Using Corpora for NLG is a full-day workshop, and
    that you do not need to register for the main conference. The
    workshop registration fee is 70 Pounds. Accommodation is available at
    the University of Birmingham. Simply select the appropriate options
    in the registration form.

    Invited Speaker
    ---------------

    Irene Langkilde-Geary (Brigham Young University, Provo, USA):
    Constraint programming as a Whiteboard Architecture for Probabilistic
    NLG.

    Regular Papers
    --------------

    Automatic Evaluation of Referring Expression Generation Using Corpora
       Surabhi Gupta and Amanda Stent, Stony Brook University, USA

    Re-Creating Dialogues from a Corpus
       Amy Isard and Carsten Brockmann, HCRC, University of Edinburgh, UK

    A Review of Recent Corpus-based Methods for Evaluating Text Structuring
    in NLG
       Nikiforos Karamanis, University of Wolverhampton, UK
       Chris Mellish, University of Aberdeen, UK

    Using an Annotated Corpus as a Knowledge Source for Language Generation
       Tomasz Marciniak and Michael Strube, EML-Research gGmbH, Germany

    The Penn Discourse TreeBank as a Resource for Natural Language Generation
       Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, Alan Lee, Eleni
       Miltsakaki, University of Pennsylvania, USA, and Bonnie Webber,
       University of Edinburgh, UK

    Statistically Generated Summary Sentences: A Preliminary Evaluation of
    Verisimilitude using Precision of Dependency Relations
       Stephen Wan, Macquarie University, Australia

    Deriving content selection rules from a corpus of non-naturally occurring
    documents for a novel NLG application
       Sandra Williams and Ehud Reiter, University of Aberdeen, UK

    Building Surface Realizers Automatically From Corpora Using
    General-Purpose Tools
       Huayan Zhong and Amanda Stent, Stony Brook University, USA

    Short corpus presentations
    --------------------------

    Ehud Reiter: Memories for Life (M4L) Corpus
    More T.B.A.

    Panel on Exploiting Corpora for NLG
    -----------------------------------

    Chris Brew, Linguistics, Ohio State University, USA
    Irene Langkilde-Geary, Brigham Young University, USA
    Ehud Reiter, Computing Science, University of Aberdeen, UK
    Donia Scott, ITRI, University of Brighton, UK
    Bonnie Webber, Informatics, University of Edinburgh, UK

    Proceedings
    -----------

    The proceedings of the workshop will be published in printed form and
    electronically on the web. We plan to publish selected papers in a
    special issue of a suitable journal.

    Workshop Co-chairs
    ------------------

    Anja Belz, ITRI, University of Brighton, UK
    Sebastian Varges, CSLI, Stanford University, USA

    Programme committee
    -------------------

    Anja Belz, ITRI, University of Brighton, UK
    John Carroll, Informatics, University of Brighton, UK
    Robert Dale, Macquarie University, Australia
    Michel Genereux, ITRI, University of Brighton, UK
    Kevin Knight, ISI, University of Southern California, USA
    Chris Mellish, University of Aberdeen, UK
    Stephan Oepen, Oslo University, Norway, and CSLI Stanford, USA
    Sebastian Varges, CSLI, Stanford University, USA

    Workshop website
    ----------------

    http://www.itri.brighton.ac.uk/ucnlg/



    This archive was generated by hypermail 2b29 : Wed Jun 15 2005 - 18:25:09 MET DST