David Vadas

dvadas1 [at] cs.usyd.edu.au

I'm a researcher in the field of Computational Linguistics. My work has been in the area of statistical parsing, specifically looking at the structure of noun phrases (NPs). I've also had a lot of experience with Combinatory Categorial Grammar (CCG) and the C&C parser.

Publications

• David Vadas (2009).
  Statistical Parsing of Noun Phrase Structure.
  PhD thesis. University of Sydney.
• David Vadas and James R. Curran (2008).
  Parsing Noun Phrase Structure With CCG.
  In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-08: HLT), pages 335-343.
  Columbus, Ohio, USA, June 15-20.
• David Vadas and James R. Curran (2007).
  Parsing Internal Noun Phrase Structure with Collins' Models.
  In Proceedings of the Australasian Language Technology Workshop (ALTW-07), pages 109-116.
  Melbourne, Australia, December 10-11.
• David Vadas and James R. Curran (2007).
  Large-Scale Supervised Models for Noun Phrase Bracketing.
  In Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics (PACLING-2007), pages 104-112.
  Melbourne, Australia, September 19-21.
• David Vadas and James R. Curran (2007).
  Adding Noun Phrase Structure to the Penn Treebank.
  In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL-07), pages 240-247.
  Prague, Czech Republic, June 23-30.
• James R. Curran, Stephen Clark, and David Vadas (2006).
  Multi-Tagging for Lexicalized-Grammar Parsing.
  In Proceedings of the Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING/ACL-06), pages 697-704.
  Sydney, Australia, July 17-21.
• David Vadas and James R. Curran (2005).
  Tagging Unknown Words with Raw Text Features.
  In Proceedings of the Australasian Language Technology Workshop (ALTW-05), pages 32-39.
  Sydney, Australia, December 10-11.
• David Vadas and James R. Curran (2005).
  Programming With Unrestricted Natural Language.
  In Proceedings of the Australasian Language Technology Workshop (ALTW-05), pages 191-199.
  Sydney, Australia, December 10-11.

Noun Phrases

Here is the NP data I annotated in the Penn Treebank. Read my thesis for the most in depth description of the annotation process, the data itself, and how I used it.

Version 1.0

In order to use the data file, you need the Penn Treebank 3 corpus. The guidelines describe the new annotations that have been added to the corpus.

• Data
• Annotation Guidelines

CCGbank

This data is the result of the CCGbank conversion process reported in Parsing Noun Phrase Structure With CCG. To use the data file, you need the CCGbank corpus.

• Data