[Corpora-List] Unsupervised Morpheme Analysis -- Morpho Challenge 2007 Workshop: Call for participation

[Mikko.Kurimo at tkk.fi]

Call for Participation:

Unsupervised Morpheme Analysis -- Morpho Challenge 2007 Workshop

In conjunction with: CLEF 2007 (Cross-Language Evaluation Forum)

Budapest, Hungary, 19 September 2007

http://www.cis.hut.fi/morphochallenge2007/

Chair: Mikko Kurimo (Helsinki University of Technology)

Morpho Challenge 2007 is part of the EU Network of Excellence PASCAL  
Challenge Program and is organized in collaboration with CLEF.


*** Topic of the Challenge and Workshop ***

The objective of the Challenge was to design a statistical machine  
learning algorithm that discovers which morphemes (smallest  
individually meaningful units of language) words consist of. 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

Morpho Challenge 2007 is a follow-up to our previous Morpho Challenge  
2005 (Unsupervised Segmentation of Words into Morphemes). The new task  
is more general in that we are not necessarily looking for an explicit  
segmentation of words this time, but a morpheme analysis of the word  
forms in the data. (For instance, the English words "boot, boots,  
foot, feet" might obtain the analyses "boot, boot + plural, foot, foot  
+ plural", respectively.)


*** Competitions ***

The submitted morpheme analysis were evaluated in two complementary ways:

     * Competition 1: The proposed morpheme analyses were compared to  
a linguistic "gold standard".
     * Competition 2: Information retrieval (IR) experiments were  
performed, where the words in the documents and queries were replaced  
by their proposed morpheme representations. The search is then based  
on morphemes instead of words.


*** Workshop Schedule (subject to change) ***

09:00 Opening
09:10 Mikko Kurimo: "Unsupervised Morpheme Analysis -- Morpho  
Challenge 2007: Introduction and Overview"
09:30 Mikko Kurimo, Mathias Creutz and Matti Varjokallio: "Competition  
1: Morpheme Analysis: Evaluation and Results. A simple reference  
method using Morfessor"
09:50 Mikko Kurimo and Ville Turunen: "Competition 2: Information  
Retrieval using the Morpheme Analysis results: Evaluation and Results"
10:20 Paul McNamee: "Applying ngrams and morpheme analysis in IR"
10:40 Discussion
11:00 Break
11:30 Delphine Bernhard: "Simple Morpheme Labelling in Unsupervised  
Morpheme Analysis"
11:50 Stefan Bordag: "Unsupervised and Knowledge-free Morpheme  
Segmentation and Analysis"
12:10 Christian Monson: "ParaMor: Finding Paradigms across Morphology"
12:30 Discussion
12:50 Conclusion


*** Program Committee ***

Levent Arslan, Bo?aziçi University
Eric Atwell, University of Leeds
Samy Bengio, Google
Tolga Cilogu, Middle-East Technical University
Kadri Hacioglu, Colorado University
Colin de la Higuera, Jean Monnet University, Saint-Etienne
Chun Yu Kit, City University of Hong Kong
Dietrich Klakow, Saarland University
James Martin, University of Colorado at Boulder
Jan Nouza,Technical University of Liberec
Erkki Oja, Helsinki University of Technology
Murat Saraçlar, Bo?aziçi University
Richard Sproat, University of Illinois, Urbana-Champaign
Richard Wicentowski, Swarthmore College


*** Further Information ***

http://www.cis.hut.fi/morphochallenge2007/



_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora