IT University of Copenhagen
We track 5 benchmarks that IT University of Copenhagen made or helped make.
0 in use 5 with public code 0 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| DanFEVER Models decide whether Danish encyclopedia evidence supports a claim, refutes it, or leaves it unresolved. The dataset contains 6,407 annotated claims. | Faithful to sources | Apr 2021 | Not in cards | |
| Kompetencer Models classify skill and knowledge phrases from Danish job ads using a European occupational taxonomy. The authors report weighted macro F1. | Other professions | Apr 2022 | Not in cards | |
| NorSID Models identify a request’s intent, tag words such as places or times, and classify the written Norwegian variety. Each task has its own score. | Reading in many languages | Oct 2024 | Not in cards | |
| Sayfullina Soft Skill Span Extraction Models mark the words that express a soft skill in English job ads. The test scores exact span matches. | Other professions | Sep 2022 | Not in cards | |
| SkillSpan Models mark the words that describe skills or knowledge in English job postings. Exact span matches determine precision, recall, and F1. | Other professions | Apr 2022 | Not in cards |