The Corpus of American Norwegian Speech (CANS)
Conference paper by Janne Bondi Johannessen in Proceedings of the 20th Nordic Conference of Computational Linguistics NODALIDA 2015, 2015.
This paper contains a description of the Corpus of American Norwegian Speech, a new tool for heritage language research. We present the background for its existence, the linguistic contents and its main technical features. The demonstration will show the corpus in use, focussing on problems that are specific to heritage language research, and how the corpus can be searched to provide relevant data.