Paper: Best Analysis Selection In Inflectional Languages

ACL ID C02-1079
Title Best Analysis Selection In Inflectional Languages
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2002

Ambiguity is the fundamental property of natural language. Perhaps, the most bur- densome case of ambiguity manifests itself on the syntactic level of analysis. In order to face up to the high number of obtained derivation trees, this paper describes several techniques for evaluation of the figures of merit, which define a sort order on parsing trees. The presented methods are based on language specific features of synthetical lan- guages and they improve the results of sim- ple stochastic approaches.