Discourse Segmentation of German Written Texts

Abstract. Discourse segmentation is the division of a text into minimal discourse segments, which form the leaves in the trees that are used to represent discourse structures. A definition of elementary discourse segments in German is provided by adapting widely used segmentation principles for English minimal units, while considering punctuation, morphology, sytax, and aspects of the logical document structure of a complex text type, namely scientific articles. The algorithm and implementation of a discourse segmenter based on these principles is presented, as well an evaluation of test runs.

• Type: Conference
• Year: 2006
• Where: FINTAL
• Authors: Harald Lüngen, Csilla Puskás, Maja Bärenfänger, Mirco Hilbert, Henning Lobin
• Keywords: Discourse, Discourse Segments, FINTAL 2006, Minimal Discourse Segments, Natural Language Processing