Cross-Language Knowledge Induction Workshop

 

International Workshop held as part of the Eurolan 2005 Summer School

25 July - 6 August, 2005,
Babes-Bolyai University, Cluj-Napoca, Romania

 

Call for Papers

 

 

NEW!!! List of accepted papers

 

The dates of the workshop are August 2, 3, 4. See updated schedule.


Knowledge of words and text behavior in other languages has recently been used to help solving tasks in a first language. An example of such a task is word-sense disambiguation by using translations in a second language. Another example is verb classification by studying properties of verbs in several languages.

 

A second modality of knowledge transfer across languages is to take advantage of resources already built for English and for a few other resource-rich languages.  These resources have been used to induce knowledge in languages for which few linguistic resources are available. This was made possible by the wider availability of parallel corpora (better alignment methods at paragraph, sentence, and word level). Examples of knowledge induction tasks are: learning morphology, part-of-speech tags, and grammatical gender. The development of wordnets for many languages used as a starting point knowledge transfer from the Princeton WordNet.

 

This workshop will provide a forum for discussion between leading names in the field and researchers involved in cross-language applications. We would like to invite researchers, master and Ph.D. students, to submit their original and unpublished work to the workshop.

 

Special consideration will be given to papers for which one of the languages involved in the knowledge transfer is an East-European language. Topics of interest include, but are not limited to:

 

·         applications that exploit parallel corpora (aligned at paragraph, sentence, or word level).

·         induction of knowledge from a language for which resources are abundant to another language for which fewer resources are available.

·         using other languages to solve a task in a first language:

o        word-sense disambiguation by using translations in other languages.

o        verb classification by studying verb properties in several languages.

o        other tasks of this kind

·         identifying and using cognate words between languages.

·         building wordnets by knowledge transfer.

·         exploiting multi-language wordnets for NLP applications.

 

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

Submission Requirements

 

Authors are invited to submit a 4-6 pages extended abstract in electronic form (pdf only) by 5th of May 2005. The review process is not blind (same as for similar workshops over the past years). Authors of accepted papers should submit the final version in electronic format not later than 20th of June. The final version must be in pdf format. If you have problems delivering your paper in pdf format, please contact the organizing committee. We can assist you with converting from Word format into pdf format. If your paper is a ps file, please convert into pdf and make sure all the fonts are included. The maximum length of the paper should be 8 pages. This workshop uses the same guidelines as ACL-2005. The instructions can be found here. Please do not insert page numbers, headers or footers. If you have any problem following the style please contact the organizing committee as soon as possible.  All the papers should be sent to diana@site.uottawa.ca

 

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

Important Dates

 

Submission Deadline: 5th May 2005

 

Notification of Acceptance: 5th June 2005

 

Camera-ready Papers: 20th June 2005

 

 

Demos of working or under development systems are encouraged.

 

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

Registration

 

People wanting to attend the workshop must be registered at the Eurolan 2005 School. Participation to the workshop is open to all Eurolan 2005 attendants. Copies of workshop proceedings will be made available. Authors of the papers accepted for presentation at the workshop will benefit of early registration fee no matter the date they register.

 

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

Programme Committee

 

Eneko Agirre (University of the Basque Country, Donostia-San Sebastián, Spain)

Paul Buitelaar (DFKI, Saarbrucken, Germany)

Silviu Cucerzan (Microsoft Research, US)

Mona Diab (Columbia University, US)

Lluís Màrquez (Universitat Politècnica de Catalunya, Barcelona, Spain)

Joel Martin (National Research Council of Canada)

Rada Mihalcea (University of North Texas, US)

Viviana Nastase (University of Ottawa, Canada)

Ted Pedersen (University of Minnesota, Duluth, US)

Emanuele Pianta  (ITC-IRST, Povo-Trento, Italy)

Philip Resnik (University of Maryland, US)

Laurent Romary (LORIA, Nancy, France)

Michel Simard (Xerox Research Centre Europe, France)

Suzanne Stevenson (University of Toronto, Canada)

Doina Tatar (Babes-Bolyai University, Cluj-Napoca, Romania)

Amalia Todirascu (Université Marc Bloch, Strasbourg, France)

Dan Tufis (Romanian Academy, Bucharest, Romania)

Nikolai Vazov (University of Sofia, Bulgaria)

 

 

Organizing committee

 

Diana Inkpen (University of Ottawa, Canada)

Carlo Strapparava (ITC-IRST, Povo-Trento, Italy)