A Divide-and-Conquer Strategy for Shallow Parsing of German Free Texts

We present a divide-and-conquer strategy based on finite state technology for shallow parsing of realworld German texts. In a first phase only the topological structure of a sentence (i.e., verb groups, subclauses) are determined. In a second phase the phrasal grammars are applied to the contents of the different fields of the main and sub-clauses. Shallow parsing is supported by suitably configured preprocessing, including: morphological and on-line compound analysis, efficient POS-filtering, and named entity recognition. The whole approach proved to be very useful for processing of free word order languages like German. Especially for the divide-andconquer parsing strategy we obtained an f-measure of 87.14% on unseen data.

• Type: Conference
• Year: 2000
• Where: ANLP
• Authors: Günter Neumann, Christian Braun, Jakub Piskorski
• Keywords: ANLP 2000, Divide-andconquer Parsing Strategy, Realworld German Texts, Shallow Parsing