Skip to main content


	title        = {SWORD: Towards Cutting-Edge Swedish Word Processing},
	abstract     = {Despite many years of research on Swedish language technology, there is still no well-documented standard for Swedish word processing covering the whole spectrum from low-level tokenization to morphological analysis and disambiguation. SWORD is a new initiative within the SWE-CLARIN consortium aiming to develop documented standards for Swedish word processing. In this paper, we report on a pilot study of Swedish tokenization, where we compare the output of six different tokenizers on four different text types.  For one text type (Wikipedia articles), we also compare to the tokenization produced by six manual annotators.},
	booktitle    = {Proceedings of the Sixth Swedish Language Technology Conference (SLTC) Umeå University, 17-18 November, 2016},
	author       = {Cap, Fabienne and Adesam, Yvonne and Ahrenberg, Lars and Borin, Lars and Bouma, Gerlof and Forsberg, Markus and Kann, Viggo and Östling, Robert and Smith, Aaron and Wirén, Mats and Nivre, Joakim},
	year         = {2016},