Smoothing fine-grained PCFG lexicons

Authors
Publication date 2009
Book title Proceedings of the 11th International Conference on Parsing Technologies (IWPT)
Event 11th International Conference on Parsing Technologies (IWPT), Paris, France
Pages (from-to) 214-217
Publisher Morristown, NJ: Association for Computational Linguistics (ACL)
Organisations
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Abstract We present an approach for smoothing treebank-PCFG lexicons by interpolating treebank lexical parameter estimates with estimates obtained from unannotated data via the Inside-outside algorithm. The PCFG has complex lexical categories, making relative-frequency estimates from a treebank very sparse. This kind of smoothing for complex lexical categories results in improved parsing performance, with a particular advantage in identifying obligatory arguments subcategorized by verbs unseen in the treebank.
Document type Conference contribution
Published at http://portal.acm.org/citation.cfm?id=1697236.1697278
Permalink to this page
Back