Projects per year
Abstract
This paper describes a wide-coverage statistical parser that uses Combinatory Categorial Grammar (CCG) to derive dependency structures. The parser differs from most existing wide-coverage treebank parsers in capturing the long-range dependencies inherent in constructions such as coordination, extraction, raising and control, as well as the standard local predicate-argument dependencies. A set of dependency structures used for training and testing the parser is obtained from a treebank of CCG normal-form derivations, which have been derived (semi-) automatically from the Penn Treebank. The parser correctly recovers over 80% of labelled dependencies, and around 90% of unlabelled dependencies.
Original language | English |
---|---|
Title of host publication | ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics |
Place of Publication | Stroudsburg, PA, USA |
Publisher | Association for Computational Linguistics |
Pages | 327-334 |
Number of pages | 8 |
DOIs | |
Publication status | Published - 2002 |
Fingerprint
Dive into the research topics of 'Building Deep Dependency Structures with a Wide-coverage CCG Parser'. Together they form a unique fingerprint.Projects
- 3 Finished
-
-
Using discourse information to control intonation and illipsis for automatic speech production
Moore, J. (Principal Investigator) & Steedman, M. (Co-investigator)
1/10/00 → 30/09/03
Project: Research
-
Wide coverage parsing and grammer induction using CCG
Steedman, M. (Principal Investigator)
30/09/00 → 29/09/03
Project: Research