scandinavian-embedding-benchmark

scandinavian-embedding-benchmark copied to clipboard

Add DDisco

2

https://danlp-alexandra.readthedocs.io/en/latest/docs/datasets.html#ddisco

KennethEnevoldsen

https://github.com/kuhumcst/danish-semantic-reasoning-benchmark

KennethEnevoldsen

https://www.mixedbread.ai/blog/mxbai-embed-large-v1

KennethEnevoldsen

Extending the dataset to other Scandinavian languages **These resources should be checked before implementing on whether they are translated or not:** - Greenlandic - Danish-Greenlandic - Greenlandic news - Icelandic...

KennethEnevoldsen

Add dataset annotation for construction

1

E.g. for ScaLA it is natural text, but synthetically augmented (and humanly evaluated). Other construction methods could include translations. Others could be found or expert-generated. It is probably reasonable to...

KennethEnevoldsen

https://huggingface.co/Salesforce/SFR-Embedding-Mistral

KennethEnevoldsen

https://huggingface.co/BAAI/bge-m3

KennethEnevoldsen

KennethEnevoldsen

https://arxiv.org/abs/2402.15449

KennethEnevoldsen

Add metadata on socioeconomic status to the datasets.

KennethEnevoldsen