Skip to main content

BibTeX

@inProceedings{Hengchen-Simon2021-305157,
	title        = {SuperSim: a test set for word similarity and relatedness in Swedish},
	abstract     = {Language models are notoriously difficult to evaluate. 
We release SuperSim, a large-scale similarity and relatedness test set for Swedish built with expert human judgments. The test set is composed of 1,360 word-pairs independently judged for both relatedness and similarity by five annotators. We evaluate three different models (Word2Vec, fastText, and GloVe) trained on two separate Swedish datasets, namely the Swedish Gigaword corpus and a Swedish Wikipedia dump, to provide a baseline for future comparison. 
We release the fully annotated test set, code, baseline models, and data.},
	booktitle    = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), May 31-June 2 2021, Reykjavik, Iceland (online)},
	author       = {Hengchen, Simon and Tahmasebi, Nina},
	year         = {2021},
	publisher    = {Linköping Electronic Conference Proceedings},
	address      = {Linköping},
	ISBN         = {978-91-7929-614-8},
}