Wordnet extension via word embeddings: Experiments on the Norwegian Wordnet

摘要

This paper describes the process of automatically adding synsets and hypernymy relations to an existing wordnet based on word embeddings computed for POS-tagged lemmas in a large news corpus, achieving exact match attachment accuracy of over 80%. The reported experiments are based on the Norwegian Word-net, but the method is language independent and also applicable to other wordnets. Moreover, this study also represents the first documented experiments of the Norwegian Wordnet.