Downloads · 30 days
10
1% of all-time downloads
ajtamayoh/NLP-CIC-WFU_Clinical_Cases_NER_Sents_tokenized_mBERT_cased_fine_tuned
NLP-CIC-WFU_Clinical_Cases_NER_Sents_tokenized_mBERT_cased_fine_tuned is a token classification model from ajtamayoh. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
1% of all-time downloads
All-time downloads
678
Public
Repo size
2.1 GB
Likes
0
Public
Click a slice to open those files.
.bin709 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-multilingual-cased on the LivingNER shared task 2022 dataset. It is available at: https://temu.bsc.es/livingner/category/data/
It achieves the following results on the evaluation set:
For a complete description of our system, please go to: https://ceur-ws.org/Vol-3202/livingner-paper13.pdf
Dataset provided by LivingNER shared task, it is available at: https://temu.bsc.es/livingner/category/data/
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0505 | 1.0 | 2568 | 0.0434 | 0.9399 | 0.6781 | 0.7878 | 0.9886 |
| 0.0393 | 2.0 | 5136 | 0.0450 | 0.9384 | 0.6947 | 0.7984 | 0.9892 |
| 0.0306 | 3.0 | 7704 | 0.0451 | 0.9497 | 0.6951 | 0.8027 | 0.9897 |
| 0.0266 | 4.0 | 10272 | 0.0422 | 0.9646 | 0.6904 | 0.8048 | 0.9900 |
| 0.0208 | 5.0 | 12840 | 0.0494 | 0.9576 | 0.6969 | 0.8067 | 0.9902 |
| 0.0141 | 6.0 | 15408 | 0.0506 | 0.8407 | 0.7352 | 0.7844 | 0.9890 |
| 0.0093 | 7.0 | 17976 | 0.0546 | 0.8574 | 0.7366 | 0.7924 | 0.9893 |
Tamayo, A., Burgos, D., & Gelbukh, A. (2022). ParTNER: Paragraph Tuning for Named Entity Recognition on Clinical Cases in Spanish using mBERT+ Rules. In CEUR Workshop Proceedings (Vol. 3202). CEUR-WS.
@inproceedings{tamayo2022partner, title={ParTNER: Paragraph Tuning for Named Entity Recognition on Clinical Cases in Spanish using mBERT+ Rules}, author={Tamayo, Antonio and Burgos, Diego and Gelbukh, Alexander} }