30 June 2000, DIP Colloquium

30 June 2000, DIP Colloquium
Title: Parse Pruning: Exploiting Author's Style
Speaker: Sonja Mueller-Landmann, Institut fuer deutsche Sprache, Mannheim
Location: OMHP, Oudemanhuispoort 4-6, Room C105.
Date and Time: Friday 30th June 2000, 15.15-17.00

Abstract:
On parsing natural language, the number of syntactically ambiguous situations inevitably grows with the coverage of the grammar. Therefore, most broad-coverage applications use one or other supplementary mechanism to decide on the respective probability of several ambiguous (partial) analyses. In this talk, I will propose corpus-based parse pruning: A database of probabilistically weighted, multi-level constituent structures is generated from a stratificational German corpus and utilized as a backbone for dependency grammar. This pruning approach yields high-quality parsing results. An extensive evaluation of the syntactic variety in the training corpus and a series of experiments on quantity and quality of the constituent structures used for pruning give further insight into the criteria that help a language model to get representative and dynamically adaptable: Corpus size, a multi-purpose annotation scheme, and a wide variety of authors.

More information can be found on the DIP (Discourse Processing) homepage, or by contacting the DIP Colloquium organizing committee at DIP@hum.uva.nl