Corpora: Final Call for papers - ws on Coherence in Generated Multimedia

From: Ivandre Paraboni (Ivandre.Paraboni@itri.brighton.ac.uk)
Date: Tue Mar 14 2000 - 14:08:51 MET

  • Next message: Linn Kinley Roby-Muller: "Corpora: Formal Spoken English"

    Apologies if you receive multiple postings.

    ==================================================================
                        Final Call for Papers

                   Coherence in Generated Multimedia

                   12 June 2000, Mitzpe Ramon, Israel

                        Workshop associated with
           International Natural Language Generation Conference
                        (INLG-2000, 13-16 June)

               http://www.cs.bgu.ac.il/~nlg2000/ws3.html
                  
    ==================================================================

                  Coherence in Generated Multimedia

    Keywords:

         - Generation of multimedia documents/presentations
         - Cross-media coreference, deixis, and anaphora
         - Media allocation, layout, and synchronization

    More and more often, Natural Language Generation is performed as
    a component of a larger Multimedia Presentation System, whose
    output consists of language and/or speech combined with graphics,
    animation, non-speech audio, etcetera. Recent years have seen
    a growing interest in various issues relevant for the design of
    such systems, such as the issue of multimedia system architecture
    (e.g., Bordegoni et al. 1997) and media allocation (e.g., ETAI
    1997-8). It is gradually becoming clear that a Multimedia
    Presentation System forces its designers to rethink some
    fundamental issues, at the core of which is a generalized notion
    of document coherence, which subsumes the purely linguistic
    notion of coherence, and which can take different forms depending
    on the type of document.

    This workshop invites submission of papers that shed light on
    the issue of discourse coherence in relation to the generation of
    documents / presentations in which *** natural language + at least
    one other medium *** play a nontrivial role. Topics of interest
    include but are not limited to:

    - Document/presentation structure. How can theories of
      discourse structure (e.g. Rhetorical Structure Theory)
      be enhanced to cover types of discourse that combine
      natural language/speech and other media?
    - Media allocation. How does the system decide what
      combination of media is used for expressing a given
      item of information, and how can authors be allowed
      to influence such decisions?
    - Interlinguality. For example, what types of semantic
      formalism are most suitable for expressing the meanings
      of expressions that use different media (e.g., pictures
      as well as text)?
    - `Fusion' of information from different media. For
      example, how can the referring expressions generated by
      a Multimedia Presentation System be simplified if the
      system is able to use pointing?
    - Cross-media coreference, deixis, and anaphora. For
      example, when are expressions like `the method illustrated
      in figure 5' felicitous, and how can a system be enabled
      to generate such expressions?
    - Media layout (in the case of a written document) and
      media synchronization (e.g., in the case of a presentation
      by a life-like agent).
    - Corpora. Multimedia corpora are an obvious potential
      source of information for multimedia generation, but
      how can connections between different media be captured?
      (E.g., how should pictures, graphs, or gestures be
      annotated?)
    - System architecture. For example, can the requirements of
      generating coherent multimedia be reconciled with the
      advantages of a pipeline architecture (e.g. Reiter 1994,
      McKeown et al. 1992)?
    - Evaluation of the quality (e.g. coherence) of documents
      or presentations generated by a Multimedia Presentation
      System.

    Presentations containing live demonstrations are welcome, but
    there is also room for purely theoretical contributions. Each
    presentation will be followed by a comment from one of the
    other participants, who will have been enabled to see the final
    version of the paper beforehand.

                           Submissions:

    Submissions (deadline: 31 March) have a preferred length of
    about 5 double-spaced pages (not counting title page, abstract,
    and references). See INLG main conference page
    (http://www.cs.bgu.ac.il/~nlg2000/) for details about the use
    of Latex (preferred) or Word. The deadline for camera-ready
    final versions is 4 May. Authors are asked to indicate
    explicitly in their submission any special requirements that
    they may have (e.g. use of VCR, internet access, data projector)
    beyond an overhead projector.

                           References:

    - AIR (1995). Special Issue "Integration of Natural Language
      and Vision Processing: Intelligent Multimedia". Artif.
      Intell. Review 9, Nos.2-3.
    - Bordegoni et al (1997). Bordegoni, Faconti, Feiner, Maybury,
      Rist, Ruggieri, Trahanias, and Wilson (1997): A Standard
      Reference Model for Intelligent Multimedia Presentation
      Systems. Computer Standards and Interfaces 18, pp.477-496.
    - ETAI (1997, 1998). ETAI News Journal on Intelligent User
      Interfaces, Vol 1, No's 1 and 2. See especially <http://
      www.dfki.de/etai/statements/reiter-nov-97-responses.html>.
    - Maybury and Wahlster (1998). Readings in Intelligent User
      Interfaces. Morgan Kaufmann, San Francisco.
    - McKeown et al. (1992). McKeown, Feiner, Robin, Seligman,
      Tanenblatt. Generating Cross-references for Multimedia
      Explanation. In Procs. of Tenth National Conf. on Artif.
      Intell., p.9-16. Menlo Park.
    - Reiter (1994). Has a Consensus NL Generation Architecture
      Appeared, and is it Psycholinguistically Plausible? In Proc.
      of 7th Int. Generation Ws. Kennebunkport, Maine.

    List of organizers (in alphabetical order)

        Elisabeth Andre (Saarbruecken)
        Phil Cohen (OGI, Oregon)
        John Lee (Co-chair, Edinburgh)
        James Lester (Raleigh, North Carolina)
        Johanna Moore (Edinburgh)
        Jon Oberlander (Edinburgh)
        Ivandre Paraboni (Brighton)
        Ehud Reiter (Aberdeen)
        Thomas Rist (Saarbruecken)
        Laurent Romary (Loria)
        Donia Scott (Brighton)
        Kees van Deemter (Co-chair, Brighton)

    Contact for questions: <Kees.van.Deemter@itri.brighton.ac.uk>

    At a later stage, there will be more information concerning the
    workshop on the web at http://www.hcrc.ed.ac.uk/~john/inlg-mm

    Submission addresses: Submissions should be sent to *both* of
    the co-chairs:

         <john@cogsci.ed.ac.uk> (John Lee)
         <Kees.van.Deemter@itri.brighton.ac.uk> (Kees van Deemter)

    Please say "INLG Multimedia ws submission" in the subject line
    of your message.

    Deadlines:

    Submissions due by 31 March
    Notification of acceptance: 21 April
    Camera-ready papers due by 4 May

    ==================================================================



    This archive was generated by hypermail 2b29 : Tue Mar 14 2000 - 19:33:33 MET