Postal Address: School of Computing, Dublin City University, Glasnevin, Dublin 9, Ireland.
Email Address: mburke@computing.dcu.ie
Phone: +353 1 700 5618
Topic: Automatic Annotation of Treebank Resources to Extract Wide-Coverage, Probabilistic Unification Grammars
Degree sought: Ph.D. in Computing
Supervisor: Dr. Andy Way and Prof. Josef van Genabith
Research Groups: National Centre for Language Technology,
Language & Intelligence Group
Deriving Quasi-Logical Forms from F-Structures for the Penn Treebank
A. Cahill, M. McCarthy, M. Burke, J. van Genabith and A. Way
in (eds.) Harry Bunt and Reinhard Muskens, Computing Meaning, Vol-3, Kluwer Academic Publishers, to appear
Evaluating Automatic F-Structure Annotation for the Penn-II Treebank
A. Cahill, M. McCarthy, M. Burke, R. O'Donovan, J. van Genabith and A. Way
in Journal of Research on Language and Computation, Kluwer Academic Publishers, to appear
Treebank-Based Acquisition of a Chinese Lexical-Functional Grammar PDF
M. Burke, O. Lam, A. Cahill, R. Chan, R. O'Donovan, A. Bodomo, J. van Genabith and A. Way
Proceedings of the 18th Pacific Asia Conference on Language, Information and Computation (PACLIC-18), pages 161-172, Tokyo, Japan
Evaluation of an Automatic Annotation Algorithm against the PARC 700 Dependency Bank PDF
M. Burke, A. Cahill, R. O'Donovan, J. van Genabith and A. Way
Proceedings of the 9th International Conference on Lexical-Functional Grammar (LFG-04), pages 101-121, Christchurch, New Zealand
Long-Distance Dependency Resolution in Automatically Acquired Wide-Coverage PCFG-Based LFG Approximations PDF PS
A. Cahill, M. Burke, R. O'Donovan, J. van Genabith and A. Way
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 320-327, Barcelona, Spain
Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank PS
R. O'Donovan, M. Burke, A. Cahill, J. van Genabith and A. Way
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 368-375, Barcelona, Spain
Treebank-Based Acquisition of Wide-Coverage, Probabilistic LFG Resources: Project Overview, Results and Evaluation PS
M. Burke, A. Cahill, R. O'Donovan, J. van Genabith and A. Way
The 1st International Joint Conference on Natural Language Processing (IJCNLP-04), Workshop "Beyond shallow analyses - Formalisms and statistical modeling for deep analyses", Sanya City, Hainan Island, China
M.Sc. by research in Computational Linguistics
Thesis: Optimised Algorithms and Data Structures for Spelling Error Detection and Correction
Summary: This thesis outlines the development of an Irish language spellchecker. The tool was designed to interface
with Microsoft Office applications for public release. An efficient spelling error detection and correction system
with a quality linguistic database was required. The process of producing directed acyclic graphs (DAGs) and corresponding
compressed file representations is described. The development of an Irish language lexicon through computational morphology techniques
is also outlined. Spelling correction techniques and average case evaluation methods are explored.
The Irish language spellchecker for Microsoft Office XP was the end product of this research.
Completed: October 2002
Supervisor: Dr. Carl Vogel
Research Group: Computational Linguistics Group, Trinity College Dublin.