Machine Learning and Cognitive Science of Language Acquisition

A PASCAL core event

An interdisciplinary workshop bringing together researchers in cognitive science and machine learning who are interested in language acquisition. Sponsored by the PASCAL network of excellence in Machine Learning. (www.pascal-network.org)

Location

University College, London

The Department of Psychology, UCL, 26 Bedford Way, London WC1A 0HP. See room details below, the main talks and the poster session will be in different rooms in this building. Directions can be found here.

Date

21 and 22 June 2007, (Thursday and Friday)

Practical information: please contact Erica Yu (erica.c.yu@gmail.com) from UCL who will be handling some of the local arrangements.

Organisers

Alex Clark, Department of Computer Science, Royal Holloway, University of London

Nick Chater, Department of Psychology, University College, London

Invited Speakers:

John Goldsmith (Departments of Linguistics and Computer Science, University of Chicago)

Chris Manning (Computer Science and Linguistics, Stanford University)

Morten Christiansen (Psychology, Cornell University)

Matthew Crocker (Psycholinguistics, Saarland University)

Walter Daelemans (Computational Linguistics and Artificial Intelligence, University of Antwerp)

Colin de la Higuera (Grammatical Inference, St Etienne)

Language acquisition and processing has been one of the central research issues in cognitive science. It is also an area in which the use of cognitive computational modelling has been especially intense. Language, and especially language acquisition, has been the key battleground for nativists and empiricists; and between advocates of rule-based, probabilistic, and connectionist models of thought. Yet the computational models proposed by CogSci researchers are often far behind, in scale and accuracy, the non-cognitively motivated models proposed by computational linguists, which are heavily based on machine learning techniques. This workshop asks how far these techniques, and their theoretical underpinnings, provide tools for building richer theories of cognitive processes. For example, can powerful machine learning techniques (e.g. kernel methods) help build models of the cognitive operations involved in human language acquisition? Conversely, can insights from cognitive science help inform and focus computational linguistic and machine learning? Can evidence concerning the spectacular computational performance of the human language processor help inspire new generations of computational linguistic and machine learning tools? This workshop will bring together participants from all of the disciplines that address this problem to discuss a range of related topics from methodological issues in computational modelling of language acquisition, including evaluation of empirical learning models, to technical problems in machine learning and grammatical inference.

The workshop includes invited talks by some of the leading researchers in these fields.

Intended audience

Cognitive scientists with an interest in language and computational modelling,

Grammatical inference researchers interested in natural language

Computational linguists interested in unsupervised learning of natural language

Machine learning researchers interested in modelling sequential data, or tree-structured data, using Bayesian, kernel-based or graphical models.

Linguists interested in computational models of language acquisition.

Psycholinguists with unexplained experimental data looking for computational models.

COLT or ALT style researchers working on formal models of learning language.

Program

The main talks will take place in the Department of Psychology, UCL, 26 Bedford Way, London WC1A 0HP. The room is Bedford Way LG04. Directions can be found here.

This is just a draft program. Any comments are welcome.

Posters

The poster session will be from 5pm to 6pm on Thursday. The room will be on the 3rd floor of the Psychology department, either the common room, or an adjacent seminar room.

Pascal logo

Valid XHTML 1.1

Page maintained by Alex Clark. Updated 19th June 2007.