Location: University of Split, Croatia
The Croatian Language Technologies Society (CLTS), the Institute for Croatian Language and Linguistics, and the School of Humanities at the University of Split are pleased to sponsor the inaugural meeting of the Workshop on Computational Linguistics held in Split, Croatia, focusing on the topic of "Computational Modeling of Lexical Acquisition". We will build on the topics in formal-theoretical and computational linguistics, in particular on issues in learnability, complexity and modeling of lexical knowledge.
This workshop is especially intended to provide a forum for the presentation of unique and original research on computational linguistic topics in the domain of learning of lexical properties, i.e. lexical acquisition, including but not limited to the following topics:
a. machine learning methods for lexical acquisition
- speech and language segmentation into lexical units
- induction and learning of phonological and morphological structure
- inducing formal grammars from discovered structural properties
- learning lexical semantic properties and lexical disambiguation
- computational models of psycholinguistic aspects of lexical acquisition
b. corpora, evaluation and applications
- induction of part-of-speech information for tagging and automatic annotation (via e.g. clustering and classification, using Vector Space Modeling or other strategies)
- corpora for learning phonological and morphological regularities and a common gold standard
- applications using machine learning and automatic lexical acquisition (e.g. tagger, ontologies, textmining)
- evaluation strategies and methods for learning approaches
This workshop will expand into a fixed annual event organized by the Croatian Language Technologies Society (CLTS) to be hosted, in turn, and shared among all interested and committed Croatian Universities.
We strongly encourage students to participate at this workshop and join the tutorial sessions!
Tutorials:
Thomas Hanneforth (University of Potsdam) "Finite State Modeling and the Potsdam FSMLib"
Damir Ćavar (Indiana University) "Vector Space Modeling, Latent Semantic Analysis, Clustering Algorithms for Lexical Acquisition"
Miroslav Martinović (The College of New Jersey) "Open Domain Question-Answering Systems - From Design to Development and Implementation"
Publications:
Papers and presentations will be published online and on a CD-ROM distributed during the workshop. All tutorial material, necessary programs and example code will be published on the workshop CD-ROM as well.
Publishers will be approached for publication of the proceedings. If you are interested or have suggestions, please contact: XYZ
Organizing Committee:
Mirjana Bonačić, University of Split
Joško Božanić, University of Split
Bojana Dalbelo Bašić, University of Zagreb
Božo Bekavac, University of Zagreb
Damir Boras, University of Zagreb
Dunja Brozović-Rončević, IHJJ Zagreb
Damir Ćavar, Indiana University
Małgorzata Ćavar, Indiana University & University of Split
Morten Christiansen, Cornell University
Zdravko Dovedan, University of Zagreb
Alexander Geyken, Berlin-Brandenburgische Akademie der Wissenschaften (BBAW)
Hans-Martin Gärtner, ZAS, Berlin
John Goldsmith, Chicago University
Thomas Hanneforth, University of Potsdam
Joshua Herring, Indiana University
Toshikazu Ikuta, Indiana University
Gerhard Jäger, University of Bielefeld
Ivo-Pavao Jazbec, University of Zagreb
Bryan Jurish, Potsdam University
Marcus Kracht, University of California, Los Angeles (UCLA)
Hagen Langer, University of Bremen
Roland Meyer, University of Regensburg
Jens Michaelis, University of Potsdam
Adam Przepiórkowski, Polish Academy of Sciences
Paul Rodrigues, Indiana University
William G. Sakas, The City University of New York (CUNY)
Giancarlo Schrementi, Indiana University
Tomislav Stojanov, University of Zagreb
Marko Tadić, University of Zagreb
Kristina Vučković, University of Zagreb
Menno van Zaanen, Macquarie University
Sponsoring Institutions:
- Ministry of Science, Education, and Sports of the Republic of Croatia
- Sveučilište u Splitu (University of Split)
- Hrvatsko društvo za jezične tehnologije (Croatian Language Technologies Society (CLTS))
- Institut za hrvatski jezik i jezikoslovlje, Zagreb (Institute for Croatian Language and Linguistics)
- ELSNET
- Microsoft
- Teched - New Generation Services