Downloads · 30 days
9
3% of all-time downloads
cross-lingual-transfer-ner-demo-1
zzzotop/cross-lingual-transfer-ner-demo-1
cross-lingual-transfer-ner-demo-1 is a token classification model from zzzotop. Use it when you need labels on individual words, such as names. It is set up for transformers.
Cross-lingual transfer demo with Faroese named entity recognition. Model is trained on Icelandic, the closest living relative. Based on 'Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroe…
All-time downloads
343
Public
Repo size
991 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin496 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Aug 24, 2023
- Updated
- Sep 4, 2023
- SHA
- bda9f731
Try a prompt
Model card
From the Hugging Face model README
Cross-lingual transfer demo with Faroese named entity recognition. Model is trained on Icelandic, the closest living relative. Based on 'Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese', Snæbjarnarson et al. (2023).
vesteinn/IceBERT finetuned on vesteinn/sosialurin-faroese-ner. Trained for 5 epochs, 22385 steps, lr 2e-5. <b>Training loop written in native pytorch.</b>
Evaluation over all batches, methodology inspired by seqeval: <br> Accuracy: 0.54808 <br> Precision: 0.54808 (micro) 0.50460 (macro) 0.31040 (weighted) <br> Recall: 0.54808 (micro) 0.75972 (macro) 0.54808 (weighted) <br> F1: 0.54808 (micro) 0.56363 (macro) 0.39525 (weighted)
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Created
- Aug 24, 2023
- Updated
- Sep 4, 2023