impresso-project/ner-hipe2020-hist-base

Impresso HIPE-2022 NER model

Token-classification (NER) model fine-tuned from dbmdz/bert-base-historic-multilingual-cased on the impresso-project/ner-augmentation dataset (HIPE-2022, NE-COARSE-LIT, IOB2). Part of the Impresso NER pipeline.

• Languages: fr, de, en
• Base model: dbmdz/bert-base-historic-multilingual-cased
• Training data: impresso-project/ner-augmentation
• Label scheme: IOB2 over NE-COARSE-LIT (pers / org / loc / prod / time).

Test-set results (seqeval, entity-level)

metric	value
f1	0.7410
loc_f1	0.8340
org_f1	0.4309
pers_f1	0.7319
precision	0.7310
prod_f1	0.6473
recall	0.7513
time_f1	0.6641

License

Inherits the CC BY-NC-SA 4.0 license of the underlying HIPE-2022 data.