Paper: Building Deep Dependency Structures Using A Wide-Coverage CCG Parser

ACL ID P02-1042
Title Building Deep Dependency Structures Using A Wide-Coverage CCG Parser
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2002
Authors

This paper describes a wide-coverage sta- tistical parser that uses Combinatory Cat- egorial Grammar (CCG) to derive de- pendency structures. The parser differs from most existing wide-coverage tree- bank 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 train- ing and testing the parser is obtained from a treebank of CCG normal-form deriva- tions, which have been derived (semi-) au- tomatically from the Penn Treebank. The parser correctly recovers over 80% of la- belled dependencies, and around 90% of unlabelled dependencies.