Learning Computational Grammars

TMR NETWORK - Learning Computational Grammars

This is the home page of the LCG TMR network.

LCG Objectives

The goals of the network are to explore machine learning techniques for natural language. These will include symbolic learning, statistical training and methods of neuro-computing. Their will be a focus on comparison of results based on attempts to learn noun phrase structure in English. Work on French and German is also possible. See the project proposal for a more detailed sketch.

LCG Partners

• University of Groningen, Netherlands (coordinator)
• University of Tuebingen, Germany
• SRI, The United Kingdom
• University of Antwerp, Belgium
• University College Dublin, Ireland
• ISSCO, University of Geneva, Switzerland
• Xerox, France

LCG Programme

The programme will apply different machine learning techniques to a set of shared tasks, viz. learning noun phrase (NP) structure from annotated textual input. The task involves recognizing NP's in text, especially their boundaries; recognizing the hierarchical tree structure within NP's; recognizing the essential grammatical roles such as head noun, modifiers and determiners (if any); recognizing the semantic roles of constituents.

The following machine learning paradigms are interesting to the LCG group: memory-based learning, data-oriented parsing and data-oriented structure processing, connectionist learning, inductive logic programming, stochastic feature grammars (and the problem of estimated feature values), explanation-based learning, transformation-based error-driven learning (based on Brill's "string transformations), genetic algorithms, semantic-driven learning, probably approximately correct learning. Postdocs may make further suggestions.

LCG is particularly interested in the degree to which the different learning techniques benefit from initial knowledge.

Please note that not all of the machine learning approaches can be tackled immediately, and that several sites have preferences among the machine learning approaches. All postdocs will be expected to contribute to common needs such as utility programs for data annotation, etc.

• Introductory Meeting, Groningen, 29 June - 3 July 1998
• General Kickoff Meeting, Cambridge, 19-21 Nov 98

LCG Opportunities

• Subject to successful contract negotiation, LCG will employ a number of post-doctoral research workers. Under unusual circumstances, research students might also receive support for training.
• All these researchers (except the one in Switzerland)
• must be under 35 years of age,
• must be EU citizens and
• must work outside their own country.
• cannot work in a country in which they have been resident for more than 18 of the previous 24 months.
• There will be opportunities for postdocs to make working visits to other LCG labs during their postdoc.
• Most of the posts will commence on the starting date of the network. They will normally last 18 or 36 months.
• Payment will be based on the 'Marie Curie' rates for TMR researchers.
• Ph.D. students who have already begun their doctoral studies may spend part of their time working with LCG.
• Post Docs at the ISSCO Lab (Geneva, Switzerland) need not be European Citizens.

For further information about any of the member labs and the range of activities there, please contact the local coordinators.

There are local preferences for some topics over others, but there is also some choice.

If you are interested in applying, send your CV, the names and addresses of two referees, and a 2-3 pp. sketch of your interest in LCG to the address below. You can do this by email if you wish. Indicate which approaches (see the detail document) and which labs interest you, and when you expect to be available. In the sketch please explain how this is related to work you have done and what special expertise you bring to the problem.

SRI, Cambridge has described its job more exactly in a separate note.)

John Nerbonne, Coordinator
Learning Computational Grammar Group
Department of Alfa-informatica
P.O. Box 716, University of Groningen
Oude Kijk in 't Jatstraat 26
NL 9700 AS Groningen, The Netherlands
phone: (31) 50 363 5815
fax: (31) 50 363 6855
email: nerbonne@let.rug.nl
www: http://www.let.rug.nl/~nerbonne/