TMR-LCG Texts

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:

• First year report (1 April 1998 - 31 March 1999) in HTML, pdf, postscript and gzipped postscript
• Second annual report (1 April 1999 - 31 March 2000) in HTML, pdf, postscript and gzipped postscript
• Third annual report (1 April 2000 - 31 March 2001) in HTML, pdf, postscript and gzipped postscript
• Fourth annual report (1 April 2001 - 31 March 2002) in pdf, postscript and gzipped postscript
• Final report in pdf, postscript and gzipped postscript

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:

• Connectionist Learning
• Data-Oriented Structure Processing
• Explanation-based learning
• Feature Estimation
• Genetic Algorithms
• Memory-Based Learning (graphical demo)
• Semantic-Driven Learning
• Transformation-Based Error-Driven Learning

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

Papers

This section contains pointers to relevant publications of network participants.

2002

• Erik F. Tjong Kim Sang, Memory-Based Shallow Parsing. Journal of Machine Learning Research, volume 2 (March), 2002, pp. 559-594. [ps.gz, pdf]
• Hervé Déjean, Learning Rules and Their Exceptions. Journal of Machine Learning Research, volume 2 (March), 2002, pp. 669-693. [ps.gz, pdf]

2001

• Erik F. Tjong Kim Sang, Transforming a Chunker to a Parser. In: Walter Daelemans, Khalil Sima'an, Jorn Veenstra and Jakub Zavrel (eds.), Computational Linguistics in the Netherlands 2000, Rodopi, 2001, pp. 177-188. [ps.gz, pdf]
• James Hammerton and Erik F. Tjong Kim Sang, Combining a self-organizing map with memory-based learning. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 9-14. [ps.gz, pdf]
• Eric Gaussier and Nicola Cancedda, Probabilistic Models for PP-attachment Resolution and NP Analysis. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 45-52. [ps.gz, pdf]
• Erik F. Tjong Kim Sang and Hervé Déjean, Introduction to the CoNLL-2001 Shared Task: Clause Identification. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 53-57. [ps.gz, pdf]
• James Hammerton, Clause identification with Long Short-Term Memory. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 61-63. [ps.gz, pdf]
• Hervé Déjean, Using ALLiS for Clausing. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 64-66. [ps.gz, pdf]
• Erik F. Tjong Kim Sang, Memory-Based Clause Identification. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 67-69. [ps.gz, pdf]
• John Nerbonne, Anja Belz, Nicola Cancedda, Hervé Déjean, James Hammerton, Rob Koeling, Stasinos Konstantopoulos, Miles Osborne, Franck Thollard and Erik F. Tjong Kim Sang, Learning Computational Grammars. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 97-104. [ps.gz, pdf]
• Alexander Clark, Unsupervised Induction of Stochastic Context-Free Grammars using Distributional Clustering. In: Walter Daelemans and Rémi Zajac (eds.), Proceedings of CoNLL-2001, Toulouse, France, 2001, pp. 105-112. [ps.gz, pdf]
• Anja Belz, Optimisation of corpus-derived probabilistic grammars. In: Proceedings of Corpus Linguistics 2001, Lancaster, UK, 2001. [ps.gz, pdf]

2000

• Stasinos Konstantopoulos, NP Chunking using ILP. In: Paola Monachesi (ed.), Computational Linguistics in the Netherlands 1999, Utrecht, The Netherlands, 2000. [ps.gz, pdf]
• Nicola Cancedda and Christer Samuelsson, Corpus-Based Grammar Specialization. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Tony Mullen and Miles Osborne, Overfitting Avoidance for Stochastic Modeling of Attribute-Value Grammars. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Hervé Déjean, ALLiS: a Symbolic Learning System for Natural Language Learning. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Erik F. Tjong Kim Sang and Sabine Buchholz, Introduction to the CoNLL-2000 Shared Task: Chunking. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Hervé Déjean, Learning Syntactic Structures with XML. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Rob Koeling, Chunking with Maximum Entropy Models. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Miles Osborne, Shallow Parsing as Part-of-Speech Tagging. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Erik F. Tjong Kim Sang, Text Chunking by System Combination. In: Proceedings of CoNLL-2000, Lisbon, Portugal, 2000. [ps.gz, pdf]
• Hervé Déjean, Theory Refinement and Natural Language Learning. In: Proceedings of COLING 2000, Saarbrücken, Germany, 2000. [ps.gz, pdf]
• Miles Osborne, Estimation of Stochastic Attribute-Value Grammars using an Informative Sample. In: Proceedings of COLING 2000, Saarbrücken, Germany, 2000. [ps.gz, pdf]
• Erik F. Tjong Kim Sang, Walter Daelemans, Hervé Déjean, Rob Koeling, Yuval Krymolowski, Vasin Punyakanok and Dan Roth, Applying System Combination to Base Noun Phrase Identification. In: Proceedings of COLING 2000, Saarbrücken, Germany, 2000. [ps.gz, pdf]
• Hervé Déjean, How to Evaluate and Compare Tagsets? A Proposal. In: Proceedings of LREC2000, Athens, Greece, 2000. [ps.gz, pdf]
• Nicola Cancedda and Christer Samuelsson, Experiments with Corpus-based LFG Specialization. In: Proceedings of ANLP-NAACL 2000, Seattle, WA, USA, 2000. [ps.gz, pdf]
• Erik F. Tjong Kim Sang, Noun Phrase Representation by System Combination. In: Proceedings of ANLP-NAACL 2000, Seattle, WA, USA, 2000. [ps.gz, pdf]

1999

• Miles Osborne, MDL-based DCG Induction for NP Induction. In: Proceedings of CoNLL-99, Bergen, Norway, 1999. [ps.gz, pdf]
• Erik F. Tjong Kim Sang and Jorn Veenstra, Representing Text Chunks. In: Proceedings of EACL'99, Bergen, Norway, 1999. [ps.gz, pdf]

The papers in postscript format have been compressed with gzip.

Talks

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

• [20010707] John Nerbonne, Learning Computational Grammars. Presented at CoNLL-2001, Toulouse, France. [ps.gz, pdf]
• [20010706] Erik F. Tjong Kim Sang and Hervé Déjean, Introduction to the CoNLL-2001 Shared Task: Clause Identification. Presented at CoNLL-2001, Toulouse, France. [ps.gz, pdf]
• [20000914] Erik F. Tjong Kim Sang and Sabine Buchholz, Introduction to the CoNLL-2000 Shared Task: Chunking. Presented at CoNLL-2000, Lisbon, Portugal. [ps.gz, pdf]
• [20000801] Erik F. Tjong Kim Sang, Walter Daelemans, Hervé Déjean, Rob Koeling, Yuval Krymolowski, Vasin Punyakanok and Dan Roth Applying System Combination to Base Noun Phrase Identification. Presented at COLING 2000, Saarbrücken, Germany. [ps.gz, pdf]
• [20000501] Erik F. Tjong Kim Sang, Noun Phrase Representation by System Combination. Presented at NAACL-2000, Seattle WA, USA. [ps.gz, pdf]
• [19990612] Erik F. Tjong Kim Sang, Noun Phrase Detection by Repeated Chunking. Presented at CoNLL-99, Bergen, Norway. [ps.gz, pdf]
• [19990611] Erik F. Tjong Kim Sang & Jorn Veenstra, Representing Text Chunks. Presented at EACL'99, Bergen, Norway. [ps.gz, pdf]

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.