Bjarte Johansen
Digital Centre of Excellence, Equinor ASA, Stavanger, Norway
Download article
Published in: Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Linköping Electronic Conference Proceedings 167:23, p. 222--231
NEALT Proceedings Series 42:23, p. 222--231
Published: 2019-10-02
ISBN: 978-91-7929-995-8
ISSN: 1650-3686 (print), 1650-3740 (online)
NER is the task of recognizing and demarcating the segments of a document that are part of a name and which type of name it is. We use 4 different categories of names: Locations (LOC), miscellaneous
(MISC), organizations (ORG), and persons (PER). Even though we employ state of the art methods---including sub-word embeddings---that work well for English, we are unable to reproduce the same success for the Norwegian written forms. However, our model performs better than any previous research on Norwegian text. The study also presents the first NER for Nynorsk. Lastly, we find that by combining Nynorsk and Bokmål into one training corpus we improve the performance of our model on
both languages.
Natural Language Processing
NLP
Named-Entity Recognition
NER
Named Entity
Norwegian
Nynorsk
Bokmål
Deep learning
