Sidsel Boldsen
Centre for Language Technology, University of Copenhagen, Denmark
Manex Agirrezabal
Centre for Language Technology, University of Copenhagen, Denmark
Download article
Published in: Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Linköping Electronic Conference Proceedings 167:44, p. 376--380
NEALT Proceedings Series 42:44, p. 376--380
Published: 2019-10-02
ISBN: 978-91-7929-995-8
ISSN: 1650-3686 (print), 1650-3740 (online)
The use of a linking element between compound members is a common phenomenon in Germanic languages. Still, the exact use and conditioning of such elements is a disputed topic in linguistics. In this paper we address the issue of predicting the use of linking elements in Danish. Following previous research that shows how the choice of linking element might be conditioned by phonology, we frame the problem as a language modeling task: Considering the linking elements -s/-? the problem becomes predicting what is most probable to encounter next, a syllable boundary or the joining element, s. We show that training a language model on this task reaches an accuracy of 94 %, and in the case of an unsupervised model, the accuracy reaches 80 %.
