Downloads · 30 days
7
1% of all-time downloads
dh-unibe/koenigsfelden-ner-v1
koenigsfelden-ner-v1 is a token classification model from dh-unibe. Use it when you need labels on individual words, such as names. It is set up for flair. The card lists the license as mit.
Downloads · 30 days
7
1% of all-time downloads
All-time downloads
688
Public
Repo size
75.1 MB
Likes
2
Public
Click a slice to open those files.
.pt75.1 MB · 50%
From the Hugging Face model README
Tagger for Medieval Scripts.
Part of the developments at the Digital Humanities@University of Bern. Developed by Ismail Prada Ziegler based on different ground truth (see below).
A model for historical German developed by Ismail Prada Ziegler as part of a research project at the University of Bern, Digital Humanities.
| PER | ORG | LOC | Micro-Avg | |
|---|---|---|---|---|
| Precision | 88.76% | 69.01% | 81.96% | 84.19% |
| Recall | 88.99% | 62.97% | 85.10% | 84.02% |
| F1-Score | 88.88% | 65.85% | 83.50% | 84.10% |
Königsfelden Charters, 14th-17th Century, Early New High German, 623k tokens training, dev, test data.
This model was a prototype with no extensive experimenting, better results can be likely be achieved on this dataset.
The documents in the dataset are published here.