English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper introduces a Scandinavian benchmarking platform, ScandEval, whichcan benchmark any pretrained model on four different tasks in the Scandinavianlanguages. The datasets used in two of the tasks, linguistic acceptability andquestion answering, are new. We develop and release a Python package andcommand-line interface, scandeval, which can benchmark any model that has beenuploaded to the Hugging Face Hub, with reproducible results. Using thispackage, we benchmark more than 100 Scandinavian or multilingual models andpresent the results of these in an interactive online leaderboard, as well asprovide an analysis of the results. The analysis shows that there issubstantial cross-lingual transfer among the Mainland Scandinavian languages(Danish, Swedish and Norwegian), with limited cross-lingual transfer betweenthe group of Mainland Scandinavian languages and the group of InsularScandinavian languages (Icelandic and Faroese). The benchmarking results alsoshow that the investment in language technology in Norway, Sweden and Denmarkhas led to language models that outperform massively multilingual models suchas XLM-RoBERTa and mDeBERTaV3. We release the source code for both the packageand leaderboard.

ScandEval: A Benchmark for Scandinavian Natural Language Processing