[Date Prev][Date Next][Date Index]

[ntcir:196] SIGIR 2006 WS on New Directions in Multilingual Info Access

            First Call for Papers
         A Workshop at ACM-SIGIR 2006
        10 August 2006, Seattle, USA

Chairs: Fredric Gey, Noriko Kando, Carol Peters, Chin-Yew Lin


Dr David A Evans, CEO of Clairvoyance Corporation
"From R&D to practice -- challenges to multilingual information
access in the real world"


May 22, 2006:    Papers submitted electronically to Chairs.
June 14, 2006:   Notice of acceptance or rejections of papers
                 sent to Authors
July 1, 2006:    Final papers submitted for workshop notebook
August 10, 2006: Workshop held in Seattle, USA

TWO KINDS OF PAPERS are sought: Short position papers (maximum
4 pages) which focus on particular areas and argue a vision of
the future in the area. Longer research scope papers (up to
10 pages) which provide depth and background as well as a
research vision. All papers will be reviewed by a program
committee and a limited number selected for presentation at
the workshop.

SUGGESTED TOPICS include but are not limited to: Multilingual
summarization, Cross-language cross-media search (speech,
video, audio), Uses of statistical MT in multilingual
information access, Less-commonly taught languages,
Cross-language text categorization, other CLIR research issues,
Multilingual named entity recognition, Multilingual digital
libraries, scalability issues in multilingual information access.


A successful workshop on "Cross-Language Information Retrieval:
A Research Roadmap" was held at SIGIR 2002 in Finland (see
http://ucdata.berkeley.edu/sigir-2002/). The 2002 workshop
attempted to establish a research agenda in Cross-Language
Information Retrieval (CLIR) for the next 5 years. The 2006
workshop will review and renew this vision. Since 2002, research
has been vigorously pursued and interesting results achieved
not only in cross-language information retrieval through the
Cross-Language Evaluation Forum (CLEF) and NTCIR Asian Language
Retrieval and Question-answering Workshop, but also in multilingual
summarization workshops and cross-language named entity
extraction challenges by the Association for Computational
Linguistics and the Geographic Information retrieval (GeoCLEF)
track of CLEF.


Another major issue is how to transition research results into
practice. This challenge has become more compelling as recent
digital content initiatives by Google, Yahoo and MSN have
inspired the European Commission to launch an effort aimed at
building The European Library. Enabling multilingual access to
the contents of Europe's national libraries will play a major
role. At the same time, the Quaero project for the development
of a European search engine was announced last summer by the
French president Jacques Chirac. Similarly, in Asia, governments
are concerned about the hegemony of US based search engines.
One goal of this workshop will be to explore whether the research
community is ready to meet the challenges posed by these major
initiatives. Can current prototype systems scale up or meet the
requirements of content and usage that such programs imply? What
is needed to move from the lab to the real world, in terms of
research, resources and equipment? How much more attention needs
to be paid to presentation of multilingual results? It is time for
the research and application communities to get together and
examine these questions in depth.

This workshop will thus have a broad scope including both research
questions and application issues. Presentations will focus on
both research and practical issues. One aim of the workshop will
be to suggest guidelines for transfer of research technology
into practice.


Fredric C. Gey
University of California, Berkeley, USA

Noriko Kando
National Institute of Informatics, Japan

Carol Peters
Italian National Research Council, Italy

Chin-Yew Lin
Microsoft Research Asia, China