Home | CFP | Shared task | Programme: Postscript | PDF

Programme CoNLL-2000 and LLL-2000

Instituto Superior Técnico, Av. Rovisco Pais, 1094-001 Lisboa, Portugal.
Tel. +351-218417000. Fax. +351-218499242.

Wednesday September 13, 2000
Shared ICGI-LLL-CoNLL session (GA)
9.00	Opening
9.15	On the Complexity of Consistent Identification of Some Classes of Structure Language Christophe Costa Florêncio
9.45	The Acquisition of Word Order by a Computational Learning System Aline Villavicencio
10.15	Corpus-Based Grammar Specialization Nicola Cancedda, Christer Samuelsson
10.45	Coffee
	CoNLL (R 02.3)	ICGI (R 01.1)
11.30	Memory-Based Learning for Article Generation Guido Minnen, Francis Bond, Ann Copestake	Computational Complexity of Problems on Probabilistic Grammars and Transducers Francisco Casacuberta, Colin de la Higuera
12.00	Using Induced Rules as Complex Features in Memory-Based Language Learning Antal van den Bosch	Probabilistic k-Testable Tree Languages Juan Ramón Rico Juan, Jorge Calera Rubio, Rafael C. Carrasco
12.30	Pronunciation by Analogy in Normal and Impaired Readers R.I. Damper, Y. Marchand	Counting Extensional Differences in BC-Learning Frank Stephan, Sebastiaan A. Terwijn
13.00	Lunch
	CoNLL (R 02.3)
14.00	Learning Distributed Linguistic Classes Stephan Raaijmakers
14.30	Knowledge-Free Induction of Morphology Using Latent Semantic Analysis Patrick Schone, Daniel Jurafsky
15.00	Modeling the Effect of Cross-Language Ambiguity on Human Syntax Acquisition William Gregory Sakas
15.30	Tea
16.00 - 18.30	CoNLL Poster Session Bullet talks and posters Using Perfect Sampling in Parameter Estimation of a Whole Sentence Maximum Entropy Language Model F. Amaya, J.M. Benedí Experiments on Unsupervised Learning for Extracting Relevant Fragments from Spoken Dialog Corpus Konstantin Biatov Generating Synthetic Speech Prosody with Lazy Learning in Tree Structures Laurent Blin, Laurent Miclet Inducing Syntactic Categories by Context Distribution Clustering Alexander Clark ALLiS: a Symbolic Learning System for Natural Language Learning Hervé Déjean Combining Text and Heuristics for Cost-Sensitive Spam Filtering Jóse M. Gómez Hidalgo, Manuel Maña López, Enrique Puertas Sanz Genetic Algorithms for Feature Relevance Assignment in Memory-Based Language Processing Anne Kool, Walter Daelemans, Jakub Zavrel Shallow Parsing by Inferencing with Classifiers Vasin Punyakanok, Dan Roth Minimal Commitment and Full Lexical Disambiguation: Balancing Rules and Hidden Markov Models Patrick Ruch, Robert Baud, Pierrette Bouillon, Gilbert Robert Learning IE Rules for a Set of Related Concepts J. Turmo, H. Rodríguez A Default First Order Family Weight Determination Procedure for WPDV models Hans van Halteren A Comparison of PCFG Models Jose Luis Verdú-Mas, Jorge Calera-Rubio, Rafael C. Carrasco
19.00 JOINT BANQUET
Thursday September 14, 2000
Shared LLL-CoNLL session (R 02.3)
9.30	Incorporating Linguistics Constraints into Inductive Logic Programming James Cussens, Stephen Pulman
10.00	Increasing our Ignorance of Language: Identifying Language Structure in an Unknown 'Signal' John Elliott, Eric Atwell, Bill Whyte
10.30	Coffee
11.00	Invited Talk: Learning in Natural Language: Theory and Algorithmic Approaches Dan Roth (University of Illinois at Urbana-Champaign)
	CoNLL (R 02.3)	LLL (R 01.1)
12.00	A Comparison between Supervised Learning Algorithms for Word Sense Disambiguation Gerard Escudero, Lluís Màrquez, German Rigau	Recognition and Tagging of Compound Verb Groups in Czech Eva Zácková, Lubos Popelínský, Milos Nepil
12.30	The Role of Algorithm Bias vs Information Source in Learning Algorithms for Morphosyntactic Disambiguation Guy De Pauw, Walter Daelemans
13.00	Lunch
14.00	Incorporating Position Information into a Maximum Entropy/Minimum Divergence Translation Model George Foster	Invited Talk: Extracting a Domain-Specific Ontology from a Corporate Intranet Jörg-Uwe Kietz, Raphael Volz, Alexander Maedche
14.30	Overfitting Avoidance for Stochastic Modeling of Attribute-Value Grammars Tony Mullen, Miles Osborne
15.00	SIGNLL Business Meeting	Learning from Parsed Sentences with INTHELEX F. Esposito, S. Ferilli, N. Fanizzi, G. Semeraro
15.30	Tea
16.00 - 18.30	CoNLL Shared Task Session Introduction to the CoNLL-2000 Shared Task: Chunking Erik F. Tjong Kim Sang, Sabine Buchholz System Descriptions Phrase Parsing with Rule Sequence Processors: an Application to the Shared CoNLL Task Marc Vilain, David Day A Context Sensitive Maximum Likelihood Approach to Chunking Christer Johansson Improving Chunking by Means of Lexical-Contextual Information in Statistical Language Models Ferran Pla, Antonio Molina, Natividad Prieto Single-Classifier Memory-Based Phrase Chunking Jorn Veenstra, Antal van den Bosch Shallow Parsing as Part-of-Speech Tagging Miles Osborne Chunking with Maximum Entropy Models Rob Koeling Learning Syntactic Structures with XML Hervé Déjean Hybrid Text Chunking GuoDong Zhou, Jian Su, TongGuan Tey Text Chunking by System Combination Erik F. Tjong Kim Sang Chunking with WPDV Models Hans van Halteren Use of Support Vector Learning for Chunk Identification Taku Kudoh, Yuji Matsumoto Discussion and Closing	Inductive Logic Programming for Corpus-Based Acquisition of Semantic Lexicons Pascale Sébillot, Pierrette Bouillon, Cécile Fabre Learning from a Substructural Perspective Pieter Adriaans, Erik de Haas Closing Session and Community Meeting