An open source part-of-speech tagger for Norwegian: Building on existing language resources

摘要

This paper presents an open source part-of-speech tagger for the Norwegian language. It describes how an existing language processing library was used to build a new part-of-speech tagger for this language. This part-of-speech tagger has been built on already available resources, in particular a Norwegian dictionary and gold standard corpus, which were partly customized for the purposes of this paper. The results of a careful evaluation show that this tagger yields an accuracy close to state-of-the-art taggers for other languages.