TMR-LCG || Participants || Meetings || Texts || Resources



Here you can find both organisatorial and scientific texts related to the TMR network "Learning Computational Grammars".

Network Proposal

The TMR-LCG Network Proposal gives an outline about the research goal, the methods that will be used and the groups that will participate. The proposal is available in HTML and in postscipt.

Annual Reports

The annual reports give an overview of the work in this project on a yearly basis. The following reports are available:

Research Tasks

The TMR-LCG Network applied different machine learning methods to the recognition of noun phrase structure. Miles Osborne and Erik Tjong Kim Sang have put forward a more elaborate definition of the common research tasks. It can be found in the first annual report of the network. Tasks which are related to our tasks are NP chunking and chunking.

The proposed first common task is NP bracketing: recognizing all NP structures in a text in which words have been annotated with part-of-speeh information. This task is the shared task of the EACL-99 workshop on Computational Natural Language Learning (CoNLL-99).

Machine Learning Methods

Different machine learning methods have been used in this research network. The following methods have been mentioned in the network proposal:

The graphical MBL demo is supplied by Antal van den Bosch.


This section contains pointers to relevant publications of network participants.





The papers in postscript format have been compressed with gzip.


This section contains pointers to sheets of some relevant talks of network participants.

The postscript sheets have been compressed with gzip. Overhead sheets of some of the talks presented at network meetings are available via the meetings page.

Last update: December 19, 2002.