BibTeX

@inProceedings{r?dveneide-2020-anforanden-302449,
	title        = {Anföranden: Annotated and Augmented Parliamentary Debates from Sweden},
	abstract     = {The Swedish parliamentary debates have been available since 2010 through the parliament’s open data web site Riksdagens öppna data. While fairly comprehensive, the structure of the data can be hard to understand and its content is somewhat noisy for use as a quality language resource. In order to make it easier to use and process – in particular for language technology research, but also for political science and other fields with an interest in parliamentary data – we have published a large selection of the debates in a cleaned and structured format, annotated with linguistic information and augmented with semantic links. Especially prevalent in the parliament’s data were end-line hyphenations – something that tokenisers generally are not equipped for – and a lot of the effort went into resolving these. In this paper, we provide detailed descriptions of the structure and contents of the resource, and explain how it differs from the parliament’s own version.},
	booktitle    = {Proceedings of the LREC 2020 Workshop on Creating, Using and Linking of Parliamentary Corpora with Other Types of Political Discourse, 11–16 May 2020},
	author       = {Rødven-Eide, Stian},
	year         = {2020},
	publisher    = {European Language Resources Association},
	address      = {Marseille, France},
	ISBN         = {979-10-95546-47-4},
}