Simple Compound Splitting for German

Simple splitting method for German compounds which combines a basic frequency-based approach with a form-to-lemma mapping to approximate morphological operations

Simple Compound Splitting for German

Typ
Tool
Autor
Marion Weller-Di Marco
Beschreibung

This simple splitting method for German compounds combines a basic frequency-based approach with a form-to-lemma mapping to approximate morphological operations.With the exception of a small set of hand-crafted rules for modeling transitional elements, this approach is resource-poor, relying only on a lemma-frequency list and a mapping from inflected to lemmatzied forms.

Example:

Häuserfassade_N → Haus_N Fassade_N

Abfüllanlage_N → abfüllen_V Anlage

Referenz

Marion Weller-Di Marco (2017): Simple Compound Splitting for German. In Proceedings of MWE 2017 (to appear)

Download

To Come.

 

Kontakt IMS

Pfaffenwaldring 5 b, 70569 Stuttgart

 

Webmaster des IMS

Zum Seitenanfang