CLEF 2000: WORKSHOP ON CROSS-LANGUAGE INFORMATION RETRIEVAL AND EVALUATION

21 - 22 September, Lisbon, Portugal

(immediately following ECDL 2000)

Description

The workshop was held over two days.

The first day was open to all those active or interested in the area of Cross-Language Information Retrieval (CLIR). The morning was dedicated to the presentation of invited papers and discussion sessions on CLIR research related issues. The afternoon addressed the topic of CLIR system evaluation: the current situation and future developments. The objective was to promote a discussion on "What is needed to improve CLIR system performance" and "How can evaluation campaigns assist in this". The goal was to identify the actual contribution of evaluation to system development and to determine what could or should be done in the future to stimulate progress.

The second day was restricted to participants in the CLEF 2000 evaluation campaign. The results of this activity were presented and discussed.

Proceedings

The Proceedings of the two-day Workshop have been published by Springer in their Lecture Notes for Computer Science series. The volume includes a record of the talks given on Day 1 and of the experiments and results of the CLEF evaluation campaign presented in Day 2. All papers have been revised and extended with respect to the preliminary draft version as a result of the discussions during the Workshop.

Day 1 - 21 September 2000

9.15 - 9.30

Opening Session

 

Welcome on behalf of the Local Coordinators, Nuno Mamede, IST-CSTC, Lisbon, Portugal
Introduction to the Workshop, Carol Peters, IEI-CNR, Pisa, Italy

 

 

9.30 - 11.00

Session 1: CLIR - What's happening now?

 

Chair: Felisa Verdejo Maillo, UNED, Madrid, Spain

9.30 - 9.50

An Overview of the Current State-of-the-Art in Multilingual Information Access
Peter Schäuble, Eurospider, Switzerland (slides)

9.50 - 10.10

New Challenges for Cross-Language Information Retrieval: multimedia data and the user experience
Gareth Jones, University of Exeter, UK (slides)

10.10 - 10.30

Multilingual Information Access: The user's perspective
Douglas W. Oard, University of Maryland, USA (slides)

10.30 - 11.00

"What is now needed in CLIR research to improve system performance?"

 

Position Papers: Fredric C. Gey, UC Berkeley, USA
Tim Gollins, University of Sheffield, UK (slides)
and Open Discussion.

 

 

11.00 - 11.30

Break

 

 

11.30 - 12.40

Session 2: Resources for CLIR

 

Chair: Michael Kluck, IZ Sozialwissenschaften, Bonn, Germany

11.30 - 11.50

Tools for Multilingual Information Access
Martin Braschler, Eurospider, Switzerland (slides)

11.50 - 12.10

May the Best Team Win: Language Resources in CLIR
Anne Diekema, Syracuse University, USA (slides)

12.10 - 12.40

"What resources are really needed and how should they be made available to the R&D community?"

 

Position Paper: Julio Gonzalo Arroyo, UNED, Madrid, Spain (slides)
and Open Discussion.

 

 

12.40 - 14.00

Lunch

 

 

14.00 - 15.30

Session 3: Issues in CLIR System Evaluation

 

Chair: Martin Braschler, Eurospider, Switzerland

14.00 - 14.20

CLIR Evaluation at TREC
Donna Harman, National Institute for Standards and Technology (NIST), USA (slides)

14.20 - 14.40

CLIR Evaluation at NTCIR
Noriko Kando, National Institute of Informatics (NII), Japan (slides)

14.40 - 15.00

CLEF: Cross-language System Evaluation for European Languages
Carol Peters, National Research Council, Pisa, Italy (slides)

 

 

15.20 - 15.50

Break

 

 

15.50 - 17.00

Panel on "CLIR Evaluation in the Future"

 

Moderator: Peter Schäuble, Eurospider, Switzerland

 

Panelists: Donna Harman, National Institute for Standards and Technology (NIST), USA
Noriko Kando, National Institute of Informatics (NII), Japan (slides)
Jussi Karlgren, SICS, Sweden (slides)
Wessel Kraaij, TNO-TPD, The Netherlands
William Ogden, Computing Research Lab, New Mexico State University, USA (slides)

 

 

Day 2 -

22 September 2000

 

 

9.00 - 9.30

CLEF 2000: Overview of the Results

 

Martin Braschler, Eurospider, Switzerland (slides)

 

 

9.30 - 10.15

Monolingual (non-English) Retrieval

 

Chair: Julio Gonzalo, UNED, Madrid, Spain

 

Presentations: Isabelle Moulinier, West Group, USA; Arjen P. de Vries, CWI, The Netherlands; Marcello Federico, ITC-irst, Italy (slides),
and Discussion.

 

 

10.15 - 10.45

Break

 

 

10.45 - 12.45

Cross-Language Retrieval

 

Chair: Donna Harman, NIST, USA

 

Presentations: Djoerd Hiemstra, University of Twente, The Netherlands; Paul McNamee, Johns Hopkins University Applied Physics Lab, USA; Turid Hedlund, Tampere University, Finland; Bärbel Ripplinger, Univ. Saarlaandes, Germany; N. Nassr, IRIT/SIG, Toulose, France; Carlos G. Figuerola, Univ. Salamanca, Spain,
and Discussion.

 

 

12.45 - 14.00

Lunch

 

 

10.45 - 12.45

Domain-Specific Retrieval

 

Chair: Michael Kluck, IZ-Bonn, Germany

 

Presentations: Norbert Goevert, Univ. Dortmund, Germany; Fred Gey, UC Berkeley, USA,
and Discussion.

 

 

15.00 - 16.30

CLEF 2001: What should we keep? What should we change? What should we add?

 

Moderator: Peter Schäuble, Eurospider, Switzerland

The draft papers outlining the approaches used by the participants in the CLEF 2000 evaluation campaign were printed in the Working Notes and distributed at the Workshop.

Workshop Steering Committee

Martin Braschler, Eurospider, Switzerland
Julio Gonzalo Arroyo, UNED, Madrid, Spain
Donna Harman, National Institute for Standards and Technology (NIST), USA
Michael Hess, University of Zurich, Switzerland
Michael Kluck, IZ Sozialwissenschaften, Bonn, Germany
Carol Peters, IEI-CNR, Pisa, Italy
Peter Schäuble, Eurospider, Switzerland

Local Coordinators

Caroline Hagège, CSTC, Lisbon, Portugal
Nuno Mamede, IST-CSTC, Lisbon, Portugal

Cross-Language Evaluation Forum

The Workshop was organised by the Cross-Language Evaluation Forum (CLEF). To find out more about the activities of CLEF, please click here.

Contact

Carol Peters - IEI-CNR
Area della Ricerca di San Cataldo, 56100 PISA (Italy)
Tel: +39 050 315 2897 - Fax: +39 050 315 2810
E-mail:
carol@iei.pi.cnr.it