SuperLim 2

Standard reference

Aleksandrs Berdicevskis, Gerlof Bouma, Robin Kurtz, Felix Morger, Joey Öhman, Yvonne Adesam, Lars Borin, Dana Dannélls, Markus Forsberg, Tim Isbister, Anna Lindahl, Martin Malmsten, Faton Rekathati, Magnus Sahlgren, Elena Volodina, Love Börjeson, Simon Hengchen, and Nina Tahmasebi. 2023. Superlim: A Swedish Language Understanding Evaluation Benchmark. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8137–8153, Singapore. Association for Computational Linguistics. Publication Bibtex

Citation

Språkbanken Text (2024). SuperLim 2 (updated: 2024-01-25). [Data set]. Språkbanken Text. https://doi.org/10.23695/kzyd-b925

Additional ways to cite the dataset.

A standardized suite for evaluation and analysis of Swedish natural language understanding systems.

See the leaderboard here. See a detailed description of the collection here.

File	Size	Modified	Licence
SuperLim-2-2.0.4.zip an archive with the whole collection (datasets, documentation sheets, additional files) (zip)	156.63 MB	2024-01-25	CC BY 4.0 attribution
SuperLim_maintenance.odt internal instructions on how (not) to update the Superlim 2.0 (odt)	16.96 KB	2024-01-25

Datasets in this collection

Resource	Type	Language	Access
Argumentation sentences 1.0 A translated corpus for classifying sentence stance in relation to a topic.	Corpus	Swedish	Dataset: argumentation-sentences.zip 2023-03-30 – 827.04 KB – CC BY 4.0
DaLAJ-GED-SuperLim 2.0 Dataset for Linguistic Acceptability Judgments (and more), v.2.0	Corpus	Swedish	Dataset: dalaj-ged-superlim.zip 2023-04-03 – 1.41 MB – CC BY 4.0 Dataset: dalaj-ged-tsv.zip 2023-05-20 – 1.15 MB – CC BY 4.0 Dataset: liuep197-11.pdf 2024-01-25 – 463.74 KB – CC BY 4.0
SuperSim (repackaged for Superlim) 2.0 A dataset for word similarity and relatedness in Swedish	Corpus	Swedish	Dataset: supersim-superlim.zip 2023-03-30 – 70.45 KB – CC BY 4.0
SweDiagnostics Swedish version of (Super)GLUE Diagnostic	Corpus	Swedish	Dataset: swediagnostics.zip 2023-04-04 – 72.89 KB – CC BY 4.0
Swedish ABSAbank-Imm 1.1 An annotated Swedish corpus for aspect-based sentiment analysis (a version of Absabank)	Corpus	Swedish	Dataset: absabank-imm.zip 2023-03-30 – 1.03 MB – CC BY 4.0
Swedish analogy 2.0 Swedish semantic and syntactic similarity	Corpus	Swedish	Dataset: sweanalogy.zip 2023-03-30 – 178.63 KB – CC BY 4.0
SweDN 1.0 A Swedish text summarization corpus	Corpus	Swedish	Dataset: swedn.zip 2023-03-30 – 89.6 MB – CC BY 4.0
SweFAQ 2.0 Frequently asked questions from Swedish authorities' websites with shuffled answers	Corpus	Swedish	Dataset: swefaq.zip 2023-03-30 – 89.81 MB – CC BY 4.0
SweNLI 1.0 A Swedish NLI dataset	Corpus	Swedish	Dataset: swenli.zip 2023-03-30 – 55.13 MB – CC BY 4.0
SweParaphrase 2.0 Semantic Textual Similarity reference data (STS Benchmark).	Corpus	Swedish	Dataset: sweparaphrase.zip 2023-03-30 – 750.9 KB – CC BY 4.0
SweSAT Swedish Scholastic Aptitude Test Synonyms 1.1 Swedish Scholastic Aptitude Test Synonyms	Lexicon	Swedish	Dataset: swesat-synonyms.zip 2023-03-30 – 37.73 KB – CC BY 4.0
SweWiC 2.0 A Swedish Word-in-Context dataset	Corpus	Swedish	Dataset: swewic.zip 2023-03-30 – 587.65 KB – CC BY 4.0
SweWinogender 2.0 A Swedish dataset for coreference and gender bias	Corpus	Swedish	Dataset: swewinogender.zip 2023-03-30 – 28.3 KB – CC BY 4.0
SweWinograd 2.0 A Swedish dataset for pronoun resolution	Corpus	Swedish	Dataset: swewinograd.zip 2023-03-30 – 33.41 KB – CC BY 4.0

(experimental feature)

Standard reference

Citation

Datasets in this collection

Type

Language

Size

Updated

Contact

DOI