Preliminary Program CLIN 2001

Please notice that this is a program which can be changed.

9.30-10.15	Registration	Charlotte Bijron & Alice Vissers	Hallen
10.15-10.30	Opening	Mariët Theune & Anton Nijholt	Hallen
10.30-11.50	Session 1A	Statistical Methods	L204, Chair: Walter Daelemans
	10.30-10.50	Conversational agents and uncertainty: using Bayesian networks for dialogue act classification	Simon Keizer (University of Twente)
	10.50-11.10	Probabilistic parsing with the Alpino grammar	Rob Malouf, Tony Mullen, Gertjan van Noord (University of Groningen)
	11.10-11.30	Unsupervised POS tagging improves parsing accuracy and parsing efficiency	Robbert Prins, Gertjan van Noord (University of Groningen)
	11.30-11.50	Applying Monte Carlo techniques to language identification	Arjen Poutsma (Smarthaven, Amsterdam)
10.30-11.50	Session 1B	Multimodal Presentation & NLG	L208, Chair: Gerard Kempen
	10.30-10.50	Kijkgedrag voor virtual agents in gesprek met de mens. Zinvol?	Ivo van Es (University of Twente)
	10.50-11.10	Modelling self-corrections in language production via underspecification and incrementality	Markus Guhe, Frank Schilder (University of Hamburg)
	11.10-11.30	Improving the 3D simulation of a car accident from a written description	Sylvain Dupuy, Arjan Egges, Pierre Nugues (ISMRA, France; University of Twente; Lund University)
	11.30-11.50	--	--
10.30-11.50	Session 1C	Corpora & Lexicon	L212, Chair: Rieks op den Akker
	10.30-10.50	Verrijking van het Parole Internet Corpus	Tilly Dutilh, Truus Kruyt, John van der Voort van der Kleij, Jesse de Does (Instituut voor Nederlandse Lexicologie, Leiden)
	10.50-11.10	A corpus-based approach to the acquisition of collocational prepositional phrases	Gosse Bouma, Begoņa Villada (University of Groningen)
	11.10-11.30	Automated compounding as a means for maximizing lexical coverage in speech recognition	Vincent Vandeghinste (University of Leuven)
	11.30-11.50	Electronic corpora for lexicographers: how we can optimise the output of quick lists consultations	Nathalie Gasiglia (University of Lille)
12.00-12.50	Invited talk	David Traum Ideas on Multi-layer dialogue management for Multi-party, Multi-conversation, Multi-modal communication	CC3
12.50-14.20	Lunch		Bastille
	14.00-14.20	Demonstrations	L200
		Amazon: Dutch Surface Parsing	Peter-Arno Coppen, Carla Schelfhout
		Performance Grammar Workbench	Gerard Kempen, Camiel van Breugel
		DRUID	Roeland Ordelman, Arjan van Hessen, Franciska de Jong
14.20-15.40	Session 2A	Machine learning I	L204, Chair: Dirk Heylen
	14.20-14.40	Conservative versus set-driven learning functions	Christophe Costa Florencio (University of Utrecht)
	14.40-15.00	PUNCTUATING PENELOPE: Memory-based clause detection applied to the final chapter of James Joyce's Ulysses	Emiel Krahmer, Antal van den Bosch (Tilburg University)
	15.00-15.20	Multi-feature error detection in spoken dialogue systems	Piroska Lendvai , Antal van den Bosch, Emiel Krahmer, Marc Swerts (Tilburg University; IPO Eindhoven)
	15.20-15.40	Phoneme-to-grapheme conversion for out-of-vocabulary items in speech recognition	Bart Decadt, Walter Daelemans, Jacques Duchateau, Patrick Wambacq (University of Antwerp; University of Leuven)
14.20-15.40	Session 2B	IR / document classification	L208, Chair: Jan van Eijck
	14.20-14.40	Developing a Dutch information retrieval test corpus	Djoerd Hiemstra (University of Twente)
	14.40-15.00	Accurate stemming and email classification	Tanja Gaustad, Gosse Bouma (University of Groningen)
	15.00-15.20	Interaction between named-entity recognition and base NP chunking for Dutch	Fien De Meulder, Veronique Hoste, Walter Daelemans (University of Antwerp)
	15.20-15.40	Using proper names to cluster documents	Dan Winchester, Mark Lee (University of Birmingham)
14.20-15.40	Session 2C	Grammars & Tools	L212, Chair: Franciska de Jong
	14.20-14.40	Performance Grammar: A uniform topological linearization model for Dutch, English and German clauses	Gerard Kempen, Karin Harbusch (Leiden University / Max Planck Institute, Nijmegen; University of Koblenz-Landau)
	14.40-15.00	The Performance Grammar Workbench: A Java applet for visual-interactive grammar development	Camiel van Breugel, Gerard Kempen (Leiden University / Max Planck Institute, Nijmegen)
	15.00-15.20	A finite-state library for NLP	Jan Daciuk, Gertjan van Noord (University of Groningen)
	15.20-15.40	The ALPINO dependency treebank	L. van der Beek, G. Bouma, R. Malouf, G. van Noord (University of Groningen)
15.40-15.55	Tea		Hallen
		Demonstrations	L200
		Amazon: Dutch Surface Parsing	Peter-Arno Coppen, Carla Schelfhout
		Performance Grammar Workbench	Gerard Kempen, Camiel van Breugel
		DRUID	Roeland Ordelman, Arjan van Hessen, Franciska de Jong
15.55-17.15	Session 3A	Machine Learning II	L204, Chair: John Nerbonne
	15.55-16.15	NP chunking using ILP	Stasinos Konstantopoulos (University of Groningen)
	16.15-16.35	Memory-based all-words word-sense disambiguation for Dutch and English	Veronique Hoste, Iris Hendrickx, Walter Daelemans, Antal van den Bosch (University of Antwerp; Tilburg University)
	16.35-16.55	Stress assignment in Dutch: Dual and single mechanism models	Gert Durieux, Evelyn Martens, Walter Daelemans, Steven Gillis, Dominiek Sandra (University of Antwerp)
	16.55-17.15	Learning Modern Greek psychological predicates	Valia Kordoni (University of Saarland)
15.55-17.15	Session 3B	Semantics & Planning	L208, Chair: Crit Cremers
	15.55-16.15	Applying knowledge graphs to model the semantics of language	Dennis Reidsma (University of Twente / Medialab BV)
	16.15-16.35	Context semantics for NL	Jan van Eijck (CWI and ILLC, Amsterdam / University of Utrecht)
	16.35-16.55	On the semantics of unrestricted how-questions	Marie Nilsenova, Balder ten Cate, Rosja Mastop (University of Amsterdam)
	16.55-17.15	BDP agents for multimodal dialogue	Rieks op den Akker, Arjan Egges, Anton Nijholt (University of Twente)
15.55-17.15	Session 3C	Syntax	L212, Chair: Gertjan van Noord
	15.55-16.15	Enriching treebanks as a knowledge source for speech recognition	Tom Laureys, Dong Hoon Van Uytsel (University of Leuven)
	16.15-16.35	On certain syntactic properties of spoken Dutch	Heleen Hoekstra, Michael Moortgat, Bram Renmans, Ineke Schuurman, Ton van der Wouden (University of Utrecht; University of Leuven)
	16.35-16.55	Parsing objectless parenthetical sentences	P.A. Coppen, C. Schelfhout (University of Nijmegen)
	16.55-17.15	--	--
17.15-18.30		Drinks	Hallen

Technical Support

Secretariat

Student helpers