[Corpora-List] Unsupervised segmentation of words into morphemes -- Challenge 2005

Mikko Kurimo mikkok at james.hut.fi
Tue Sep 13 12:58:00 CEST 2005


(I believe this competition call may interest some people in corpora.)

http://www.cis.hut.fi/morphochallenge2005/
email: morphochallenge2005 at james.hut.fi

Unsupervised segmentation of words into morphemes -- Challenge 2005

Part of the EU Network of Excellence PASCAL Challenge
Program. Participation is open to all.

The objective of the Challenge is to design a statistical machine
learning algorithm that segments words into the smallest
meaning-bearing units of language, morphemes. Ideally, these are basic
vocabulary units suitable for different tasks, such as text
understanding, machine translation, information retrieval, and
statistical language modeling.

The scientific goals are:

* To learn of the phenomena underlying word construction in
natural languages
* To discover approaches suitable for a wide range of languages
* To advance machine learning methodology

The results will be presented in the Challenge workshop in April.

Program Committee:

Levent Arslan, Boğaziçi University
Samy Bengio, IDIAP
Tolga Cilogu, Middle-East Technical University
John Goldsmith, University of Chicago
Kadri Hacioglu, Colorado University
Chun Yu Kit, City University of Hong Kong
Dietrich Klakow, Saarland University
Jan Nouza,Technical University of Liberec
Erkki Oja, Helsinki University of Technology
Richard Wicentowski, Swarthmore College

Please read the rules and see the schedule. The datasets are available
for download.

We are looking forward to an interesting competition!

Mikko Kurimo, Mathias Creutz and Krista Lagus
Neural Networks Research Centre, Helsinki University of Technology
The organizers

http://www.cis.hut.fi/morphochallenge2005/
email: morphochallenge2005 at james.hut.fi






More information about the Corpora-archive mailing list