All resources
Models, datasets, and tools for Slovak: 31 resources from 7 teams and other authors.
5 resources
Embedding models and datasets for searching, comparing, and clustering texts by meaning.
Compare in the SkMTEB — Slovak Text Embedding Benchmark benchmark- ModelBGE-M3
BGE-M3 is a new embedding model, which is distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity.
Search by meaning- University of Science and Technology of China
- BAAI
Search by meaning– - DatasetSkMTEB
SkMTEB is the first comprehensive MTEB-style text embedding benchmark for Slovak — a low-resource West Slavic language with ~5 million speakers.
Search by meaning- SlovakNLP Community
Search by meaningCC BY 4.0 - ModelE5-sk-large
This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search,…
Search by meaningMIT - ModelE5-sk-small
This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search,…
Search by meaningMIT - DatasetSlovak STS Synthetic
This is a synthetic Slovak dataset intended for the semantic textual similarity (STS) task.
Search by meaningCC BY-NC 4.0