CALL FOR PAPERS
29 June 2007, Prague, Czech Republic
Workshop Description
The past decades have seen a massive expansion in the application of statistical and machine learning methods to natural language processing (NLP). This work has yielded impressive results in numerous speech and language processing tasks, including e.g. speech recognition, morphological analysis, parsing, lexical acquisition, semantic interpretation, and dialogue management. The good results have generally been viewed as engineering achievements.
Recently researchers have begun to investigate the relevance of computational learning methods for research on human language acquisition. These investigations are very important since if computational techniques can be used to improve our understanding of human language acquisition, this will not only benefit cognitive sciences in general but will reflect back to NLP and place us in a better position to develop useful language models.
Some examples of recent investigations include:
- statistical lexical acquisition and analysis of
corpora to gain more accurate descriptions of the learning environment, to
investigate the lexical properties of developmental stages, and to quantify
differences between child and adult productions;
- computational models which investigate the
capabilities of particular theories (notably the benefit and practicality of
Universal Grammar);
- biologically motivated neural networks which
investigate the acquisition of specific lexical
constructions.
Success in this type of research requires close collaboration between NLP and cognitive scientists. To this end, interdiciplinary workshops can play a key role in advancing existing and initiating new research. This was demonstrated by two successful workshops held at COLING 2004 and ACL 2005 which focussed on psycho-computational models of human language acquisition. However, in general, there has been little space at major NLP conferences for cognitive aspects of language acquisition. Even CoNLL which was originally intended to provide a venue for research on (psycho)linguistically relevant machine learning work has only occasionally provided a forum for work.
Target Audience
Our workshop aims to bring together researchers from the diverse fields of NLP, machine learning, artificial intelligence, (psycho)linguistics, etc. who are interested in the relevance of computational techniques for understanding human language learning. The workshop is intended to bridge the gap between the computational and cognitive communities, promote knowledge and resource sharing, and help initiate interdiciplinary research projects.
Areas of Interest
Papers are invited on, but not limited to, the following topics:
- Computational learning theory and analysis of
language learning
- Computational models of human (first, second and
bilingual) language acquisition
- Computational models of various components of the
language faculty and their impact on the acquisition task
- Computational models of the evolution of
language
- Data resources and tools for investigating
computational models of human language acquisition
- Empirical and theoretical comparisons of the
learning environment and its impact on the acquisition task
- Computational methods for acquiring various
linguistic information (related to e.g. speech, morphology, lexicon, syntax,
semantics, and discourse) and their relevance to research on human language
acquisition
- Investigations and comparisons of supervised,
unsupervised and weakly-supervised methods for learning (e.g. machine
learning, statistical, symbolic, biologically-inspired, active learning,
various hybrid models) from the cognitive aspect
Papers can cover one or more of these areas.
Workshop Program
8:55-9:00 Welcome
9:00-9:45 Invited Talk
Suzanne Stevenson
University of Toronto
9:45-10:15 A Linguistic Investigation into Unsupervised DOP
Rens Bod
10:15-10:45 Using Classifier Features for Studying the Effect of Native Language on the Choice of Written Second Language Words
Oren Tsur and Ari Rappoport
10:45-11:15 MORNING COFFEE BREAK
11:15-11:45 Phon 1.2: A Computational Basis for Phonological Database Elaboration and Model Testing
Yvan Rose, Gregory Hedlund, Rod Byrne, Todd Wareham and Brian MacWhinney
11:45-12:15 High-accuracy Annotation and Parsing of CHILDES Transcripts
Kenji Sagae, Eric Davis, Alon Lavie, Brian MacWhinney and Shuly Wintner
12:15-12:45 I will shoot your shopping down and you can shoot all my tins — Automatic Lexical Acquisition from the CHILDES Database
Paula Buttery and Anna Korhonen
12:45-14:15 LUNCH
14:15-14:45 A Cognitive Model for the Representation and Acquisition of Verb Selectional Preferences
Afra Alishahi and Suzanne Stevenson
14:45-15:15 ISA meets Lara: An incremental word space model for cognitively plausible simulations of semantic learning
Marco Baroni, Alessandro Lenci and Luca Onnis
15:15-15:45 Simulating the acquisition of object names
Alessio Plebe, Vivian De La Cruz and Marco Mazzone
15:45-16:15 AFTERNOON BREAK
16:15-16:45 Rethinking the syntactic burst in young children
Christophe Parisse
16:45-17:15 The Topology of Synonymy and Homonymy Networks
James Gorman and James Curran
17:15-17:45 The Benefits of Errors: Learning an OT Grammar with a Structured Candidate Set
Tamas Biro
17:45-18:15 Learning to interpret novel noun-noun compounds: evidence from a category learning experiment
Barry Devereux and Fintan Costello
18:15-18:20 Closing Remarks
Important Dates
Paper submission deadline: 26 March 2007
Acceptance notification sent: 25 April 2007
Final version deadline: 9 May 2007
Workshop date: 29 June 2007
Workshop Chairs
Paula Buttery
University of Cambridge, UK
Aline Villavicencio
Federal University of Rio Grande do Sul, Brazil
University of Bath, UK
Anna Korhonen
University of Cambridge, UK
Address any queries regarding the workshop to: cognitive-2007@cl.cam.ac.uk
Program Committee
Colin J Bannard (Max Planck Institute for Evolutionary Anthropology, Germany)
Robert C. Berwick (Massachusetts Institute of Technology, USA)
Jim Blevins (University of Cambridge, UK)
Antal van den Bosch (Tilburg University, The Netherlands)
Chris Brew (Ohio State University, USA)
Ted Briscoe (University of Cambridge, UK)
Alexander Clark (Royal Holloway, University of London, UK)
Robin Clark (University of Pennsylvania, USA)
Stephen Clark (University of Oxford, UK)
Matthew W. Crocker (Saarland University, Germany)
James Cussens (University of York, UK)
Walter Daelemans (University of Antwerp, Belgium and Tilburg University, The Netherlands)
Bruno Gaume (Universite Paul Sabatier, France)
Ted Gibson (Massachusetts Institute of Technology, USA)
Henriette Hendriks (University of Cambridge, UK)
Julia Hockenmaier (University of Pennsylvania, USA)
Marco Idiart (Federal University of Rio Grande do Sul, Brazil)
Mark Johnson (Brown University, USA)
Gea de Jong (University of Cambridge, UK)
Aravind Joshi (University of Pennsylvania, USA)
Gerard Kempen (Leiden University, Netherlands)
Brian MacWhinney (Carnegie Mellon University, USA)
Martin Pickering (University of Glasgow, UK)
Thierry Poibeau (University Paris 13, France)
Brechtje Post (University of Cambridge, UK)
Ari Rappoport (The Hebrew University of Jerusalem, Israel)
Kenji Sagae (University of Tokyo, Japan)
Sabine Schulte im Walde (University of Stuttgart, Germany)
Mark Steedman (University of Edinburgh, UK)
Suzanne Stevenson (University of Toronto, Canada)
Bert Vaux (University of Wisconsin, USA)
Charles Yang (University of Pennsylvania, USA)
Menno van Zaanen (Macquarie University, Australia)
Registration
Information on registration is provided at the ACL-2007 website.
This page is maintained by Anna Korhonen. Last updated 25.5.2007.