• Base vocabulary pool

  ---

• Models for wordform-baseform mapping

  ---

• Models for part-of-speech tagging

  ---

Resources by Eva Forsbom

Base vocabulary pool

A base vocabulary pool, i.e. a general-purpose base vocabulary consisting of a ranked list of the most generally used lemmas, their wordforms, adjusted frequency, and contribution. From this pool, base vocabularies for various application needs can be extracted.

Models for wordform-baseform mapping

Models for Swedish baseform conversion (or wordform generation), to be used in a wordform-baseform mapper (or elsewhere). The models are various subsets and variants of the base vocabulary pool.

Models for part-of-speech tagging

Models for Swedish part-of-speech tagging, to be used with a part-of-speech tagger. The models are trained with various corpora and tagsets for various taggers.