Cross-Language Knowledge Induction Workshop
International Workshop held as part of the
EuroLAN 2005 Summer School
August 2-4, 2005
Editors: Diana Inkpen and Carlo Strapparava
Jesus Gimenez, Lluís Màrquez, and German Rigau
Eneko Agirre, Aitziber Atutxa, Koldo Gojenola, Kepa Sarasola, and David Terrón
Oana Frunza, Diana Inkpen, and David Nadeau
Sebastian Padó and Katrin Erk
Verginica Barbu Mititelu and Radu Ion
Bruno Cavestro and Nicola Cancedda
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 provides a forum for discussion between leading names in the field and researchers involved in cross-language applications. 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 (word-sense disambiguation by using translations in other languages, verb classification by studying verb properties in several languages, and other tasks of this kind); identifying and using cognate words between languages; building wordnets by knowledge transfer; and exploiting multi-language wordnets for NLP applications.
We would like to thank all the authors who submitted papers for the hard work that went behind their submissions. We express our deepest gratitude to the committee members for their thorough reviews. We also thank the EuroLAN 2005 organizers for their help with administrative matters.
Agirre (University of the Basque Country, Donostia-San Sebastián,
Mona Diab (Columbia University, US)
Lluís Màrquez (Universitat Politècnica de Catalunya, Barcelona, Spain)
Martin (National Research Council of
Emanuele Pianta (ITC-IRST, Povo-Trento, Italy)
Simard (Xerox Research Centre Europe,
Todiraşcu (Université Marc Bloch,
Carlo Strapparava (ITC-IRST, Povo-Trento, Italy)