Adapting Data Mining for German Named Entity Recognition
Résumé
In the latest decades, machine learning approaches have been intensively exper-imented for natural language processing. Most of the time, systems rely on using statistics within the system, by analyzing texts at the token level and, for labelling tasks, categorizing each among possible classes. One may notice that previous sym-bolic approaches (e.g. transducers) where designed to delimit pieces of text. Our re-search team developped mXS, a system that aims at combining both approaches. It lo-cates boundaries of entities by using se-quential pattern mining and machine learn-ing. This system, intially developped for French, has been adapted to German.
Domaines
Informatique et langage [cs.CL]
Origine : Fichiers produits par l'(les) auteur(s)
Loading...