Xlm-roberta-large model fine-tuned on UD and eFontes corpora, to optimize and enhance NER task on Polish medieval Latin texts from different genres.
Special emphasis was put on latinized Polish entities such as village, region and human names.
This is work in progress. Tag names are in Polish but will be converted to standard NER tags soon.
- Downloads last month
- 18
Inference API (serverless) is not available, repository is disabled.