[Corpora-List] CfP: Special Issue of JNLE on Interactive QA

From: Nick Webb (nwebb@albany.edu)
Date: Tue Oct 31 2006 - 17:47:27 MET

  • Next message: mtjoseph@umich.edu: "[Corpora-List] A WIKI FOR COMPUTATIONAL LINGUISTICS"

    CALL FOR PAPERS

    Journal Of Natural Language Engineering: Special Issue on Interactive
    Question Answering

    GUEST EDITORS:

    Nick Webb (SUNY Albany, USA)
    Bonnie Webber (University of Edinburgh, UK)

    IMPORTANT DATES:

    1st March 2007 Deadline for submissions
    1st July 2007 Notification
    1st October 2007 Final copy due

    Following the successful workshop on Interactive Question Answering
    (IQA), held at HLT-NAACL in June 2006, we are pleased to announce a
    special issue of the Journal of Natural Language Engineering on
    IQA. This special issue is open to all submissions relevant to this
    topic, and is not restricted to papers presented at the IQA workshop.

    MOTIVATION

    In moving beyond simple factoid Question Answering (QA), it has become
    clear 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. Users both want to and can do a lot
    more, such as ask a wider range of question types and respond to the
    system's answer in more ways than with another factual question. Real
    users can leverage greater mixed-initiative interactive question and
    answer capabilities, with coherent targeted answers presented in
    context for easy inspection. Repeat users may want to assume that the
    system remembers information from their previous interactions -- i.e.,
    in the form of a user model.

    Such developments move the paradigm of QA away from single question,
    single answer modalities, toward Interactive QA, where the system
    retains memory of the QA process, and where users develop their
    understanding of a situation through a fully interactive QA
    dialogue. Dialogue systems already allow users to interact with
    simple, structured data such as train or flight timetables, usually
    though a dialogue component based on some variation of finite-state
    models. Such models make intensive use of the structure of the domain
    to constrain the range of possible interactions -- a constraint that
    it will be difficult to fulfil in the large or even in open domain
    scenarios that are often the target for QA systems.

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

    (2) Answer structure and presentation
    - Supporting interaction about answers
    - Enabling the user to understand the range of choices, or the
      complexity of the data

    (3) Models of dialogue
    - Using domain knowledge to conduct and constrain interactions
      appropriately
    - Characterising generic, generally-applicable types of QA
      interactions
    - Engaging in sub-dialogues for clarification, error-correction,
      negotiation, etc.

    (4) 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 are nevertheless sufficient to conduct interactions over
      different data

    (5) Evaluation
    - User centred evaluation
    - Subjective component to measure: Interaction effectiveness; Results
      quality; Cognitive load of IQA vs. alternative search methods

    SUBMISSIONS

    We are expecting full papers to describe original, previously
    unpublished research.

    Papers should be formatted according to the NLE journal instructions,
    and should not exceed 20 pages. The preferred formatting system is LaTeX,
    which can be used for direct typesetting, and a style file is available
    through anonymous ftp from the following address:

    ftp.cup.cam.ac.uk/pub/texarchive/journals/latex/nle-sty/.

    In case of difficulty there is a helpline available on e-mail:

    texline@cup.cam.ac.uk.

    Send your submission (a PostScript or PDF file) to Nick Webb
    (nwebb@albany.edu).

    GUEST EDITORIAL BOARD

    Roberto Basili (Universita di Roma, "Tor Vergata", Italy)
    Johan Bos (Universita di Roma, "La Sapienza", Italy)
    Jennifer Chu-Carroll (IBM, USA)
    Anette Frank (DFKI, Germany)
    Sanda Harabagiu (LCC, USA)
    Ryuichiro Higashinaka (NTT, Japan)
    Udo Kruschwitz (University of Essex, UK)
    Oliver Lemon (University of Edinburgh, UK)
    Steven Maiorano (AQUAINT Technical Steering Committee, USA)
    Joe Polifroni (University of Sheffield, UK)
    Sharon Small (SUNY, Albany, USA)
    Tomek Strzalkowski (SUNY, Albany, USA)
    Yorick Wilks (University of Sheffield, UK)

    ABOUT THE JOURNAL

    Natural Language Engineering is an international journal designed to
    meet the needs of professionals and researchers working in all areas of
    computerised language processing, whether from the perspective of
    theoretical or descriptive linguistics, lexicology, computer science
    or engineering. Its principal aim is to bridge the gap between
    traditional computational linguistics research and the implementation
    of practical applications with potential real-world use. As well as
    publishing research articles on a broad range of topics from text
    analysis, machine translation and speech generation and synthesis to
    integrated systems and multi modal interfaces the journal also
    publishes book reviews. Its aim is to provide the essential link
    between industry and the academic community.

    Natural Language Engineering encourages papers reporting research with
    a clear potential for practical application. Theoretical papers that
    consider techniques in sufficient detail to provide for practical
    implementation are also welcomed, as are shorter reports of on-going
    research, conference reports, comparative discussions of NLE products,
    and policy-oriented papers examining e.g. funding programs or market
    opportunities. All contributions are peer reviewed.

    Editors:

    Professor John I. Tait
    University of Sunderland, UK

    Dr. Branimir K. Boguraev
    IBM Thomas J. Watson Research Center, New York, USA

    Professor Ruslan Mitkov
    University of Wolverhampton, UK

    Professor Martha Palmer
    University of Colorado at Boulder, USA

    -- 
    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 : Tue Oct 31 2006 - 17:47:22 MET