[Corpora-List] CFP: HLT-NAACL06 Workshop on Interactive QA

From: Nick Webb (nwebb@albany.edu)
Date: Mon Jan 09 2006 - 16:17:40 MET

  • Next message: Juliane Fluck: "[Corpora-List] Second International Symposium on Semantic Mining in Biomedicine (SMBM) - Final Call for Papers"

    [apologies for multiple postings]

    Call for papers for the

    Workshop on Interactive Question Answering

    http://www.ils.albany.edu/IQA06/

    8th & 9th June 2006 - New York City, USA
    to be held as part of the HLT-NAACL conference in New York City
    (http://nlp.cs.nyu.edu/hlt-naacl06/)

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

    Full Paper Submission: March 3rd, 2006
    Acceptance Notification: March 31st, 2006
    Camera-Ready Papers due: April 21st, 2006
    Workshop: June 8th & 9th, 2006

    -----------
    DESCRIPTION
    -----------

    In moving from factoid Question Answering (QA) to answering complex
    questions, it has become apparent that insufficient attention has been
    paid to the user's role in the process, other than as a source of one-
    shot
    factual questions or a sequence of related questions. Rather, users
    both want to
    and can do a lot more: With respect to answers, users can usually
    disambiguate between a range of possible factoid answers and/or
    navigate information clusters in an answer space; With respect to
    the QA process, users want to ask more types of questions and respond
    to the system's answer in more ways than another factual question.
    In short, real users demand real-time interactive question and answer
    capabilities, with coherent targeted answers presented in context for
    easy inspection. Repeat users will require user models that treat
    information already provided as background to novel information that
    is now available.

    Such developments move the paradigm of QA away from single question,
    single answer modalities, toward interactive QA, where the system may
    retain memory of the QA process, and where users develop their
    understanding of a situation through an interactive QA dialogue.
    Dialogue
    systems already allow users to interact with simple, structured data
    such
    as train or flight timetables, using a dialogue component based on
    variations of finite-state models. Such models make intensive use of the
    structure of the domain to constrain the range of possible
    interactions.

    To move forward, one needs the combined capabilities of dialogue
    systems and open-domain QA systems. We therefore solicit papers
    relevant to achieving this goal, which may touch on one or more of the
    following key issues:

    ----------
    KEY ISSUES
    ----------

    (1) Models of the domain
    - a priori models which give a deeper, more consistent representation of
        the data
    - models built on the fly, which may be shallower, or more coarse grain,
        but which may be sufficient to conduct interactions over a wide
        range of data

    (2) Models of dialogue
    - Using domain knowledge to conduct and constrain interactions
    appropriately
    - Generic, generally-applicable types of QA interactions
    - clarification sub-dialogues, error-correcting dialogues and
    negotiation
        dialogues

    (3) Integration
    - Using dialogue models in open-domain QA (for question
        expansion, answer candidate ranking, etc.)
    - Integrating closed and open domain QA to support dialogue

    (3) Answer presentation
       - enable the user to understand the range of choices, or the
    complexity
         of the data

    (4) Evaluation
    - user centred evaluation
    - subjective component to measure:
            - effectiveness of interaction
            - quality of results
            - percent of cognitive load compared to alternative search mechanisms

    --------------------------
    ROADMAP FOR INTERACTIVE QA
    --------------------------

    The goal of this two day workshop is to explore the area of dialogue
    as applied to
    the QA scenario, to extend current technology beyond factoid QA. We
    would
    like the workshop to produce some tangible output, at the very least a
    blueprint for the potential development of the field. Each of the
    keynote
    speakers will add something to the discussion about the future direction
    of interactive QA (or past developments), relating to the four research
    goals listed above. During these presentations, and the presentations of
    the participants, notes will be taken about research priorities,
    existing
    systems, methodologies and principles. At the end of the workshop, there
    will be a discussion section to produce a roadmap for the future
    development of interactive QA systems. This roadmap will be
    circulated to
    participants after the event. Such a roadmap has many potential uses -
    including galvanising research funding bodies to support efforts in the
    suggested areas.

    ----------------
    KEYNOTE SPEAKERS
    ----------------

    The invited keynote speakers to this workshop are intended to set the
    scene for the range of papers which follow. Keynote speakers will
    include:

    Bill Woods (SUN Microsystems)
    Heather McCallum-Bayliss (ARDA)
    Jim Hieronymous (NASA)
    Tomek Strzalkowski (SUNY, Albany)

    -------------
    PARTICIPATION
    -------------

    This workshop aims to bring together practitioners from a variety of
    disciplines - Information Retrieval, QA and Dialogue Systems - to
    highlight the challenges and range of potential solutions to the now
    reborn, still young, but growing interactive QA community. To do so
    at an
    early stage of interactive system development can help researchers to
    understand the full range of techniques, approaches and toolkits
    available
    from different research communities.

    -----------
    SUBMISSIONS
    -----------

    Authors are required to provide a Portable Document Format (PDF) version
    of their papers. The submission must be electronic. The proceedings will
    be printed on US-Letter paper. Manuscripts must be in two-column
    format of
    ACL proceedings (11pt Times-Roman font). Exceptions to the two-column
    format include the title, authors' names and complete addresses, which
    must be centred at the top of the first page, and any full-width figures
    or tables.

    For the workshop, the maximum length of a manuscript is eight (8)
    pages for full papers printed single-sided. Authors are strongly
    encouraged to use the LaTeX style files or MSWord equivalents available
    from http://nlp.cs.nyu.edu/hlt-naacl06/styles/.

    Tom make a submission, please use the START server, located at:

    http://www.softconf.com/start/HLT-WS06-IQA/

    -----------------
    PROGRAM COMMITTEE
    -----------------

    - Roberto Basili (University of Rome, Tor Vergata)
    - John Donelan (AQUAINT Technical Steering Committee)
    - Sanda Harabagiu (LCC)
    - Ryuichiro Higashinaka (NTT)
    - Udo Kruschwitz (University of Essex)
    - Oliver Lemon (University of Edinburgh)
    - Steven Maiorano (AQUAINT Technical Steering Committee)
    - Joe Polifroni (University of Sheffield)
    - Sharon Small (SUNY, Albany)
    - David Traum (ICT)
    - Nick Webb (SUNY, Albany)
    - Bonnie Webber (University of Edinburgh)

    -- 
    

    Nick Webb: Senior Research Scientist Institute of Informatics, Logics and Security Studies University at Albany: State University of New York tel: +1 (518) 4423082 www: http://www.nick-webb.net fax: +1 (518) 4422606 email: nwebb@albany.edu



    This archive was generated by hypermail 2b29 : Mon Jan 09 2006 - 16:19:27 MET