A Stochastic Topological Parser of German

Markus Becker; Anette Frank

In: Proceedings of COLING 2002. International Conference on Computational Linguistics (COLING), Taipei, Taiwan, Province of China, Pages 71-77, 2002.


We present a new approach to topological parsing of German which is corpus-based and built on a simple model of probabilistic CFG parsing. The topological field model of German provides a linguistically motivated, macro structure for complex sentences. Besides the practical aspect of developing a robust and accurate topological parser for hybrid shallow and deep NLP, we investigate to what extent topological structures can be handled by context-free probabilistic models. We discuss experiments with systematic variants of a topological treebank grammar, which yield competitive results. (ps, 56 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence