NorBench -- A Benchmark for Norwegian Language Models
About
We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics. We also introduce a range of new Norwegian language models (both encoder and encoder-decoder based). Finally, we compare and analyze their performance, along with other existing LMs, across the different benchmark tests of NorBench.
David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja {\O}vrelid, Egil R{\o}nningstad, Elina Sigdel, Anna Palatkina• 2023
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Question Answering | MedMCQA (test) | -- | 48 | |
| De-identification | Nor-DeID (test) | F1-score88.49 | 6 | |
| Medical Question Paraphrasing | MedMQP (test) | F1-score64.04 | 6 |
Showing 3 of 3 rows