Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,53 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- as
|
| 5 |
+
base_model:
|
| 6 |
+
- google/muril-large-cased
|
| 7 |
+
pipeline_tag: token-classification
|
| 8 |
+
tags:
|
| 9 |
+
- NER
|
| 10 |
+
- Named_Entity_Recognition
|
| 11 |
+
pretty_name: APTFiNER Tamil XLM-RoBERTa
|
| 12 |
+
datasets:
|
| 13 |
+
- prachuryyaIITG/CLASSER
|
| 14 |
+
metrics:
|
| 15 |
+
- f1
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
**MuRIL is fine-tuned on Assamese CLASSER dataset XLM-RoBERTa model for Fine-grained Named Entity Recognition.**
|
| 19 |
+
|
| 20 |
+
## Model performance:
|
| 21 |
+
Precision: 74.88 <br>
|
| 22 |
+
Recall: 75.62 <br>
|
| 23 |
+
**F1: 75.25** <br>
|
| 24 |
+
|
| 25 |
+
## Training Parameters:
|
| 26 |
+
Epochs: 6 <br>
|
| 27 |
+
Optimizer: AdamW <br>
|
| 28 |
+
Learning Rate: 5e-5 <br>
|
| 29 |
+
Weight Decay: 0.01 <br>
|
| 30 |
+
Batch Size: 64 <br>
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
## Citation
|
| 34 |
+
|
| 35 |
+
If you use this model, please cite the following papers:
|
| 36 |
+
|
| 37 |
+
```bibtex
|
| 38 |
+
@inproceedings{kaushik2025classer,
|
| 39 |
+
title = {{CLASSER}: Cross-lingual Annotation Projection enhancement through Script Similarity for Fine-grained Named Entity Recognition},
|
| 40 |
+
author = {Kaushik, Prachuryya and Anand, Ashish},
|
| 41 |
+
booktitle = {Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
|
| 42 |
+
year = {2025},
|
| 43 |
+
publisher = {Association for Computational Linguistics},
|
| 44 |
+
note = {Main conference paper}
|
| 45 |
+
}
|
| 46 |
+
|
| 47 |
+
@inproceedings{kaushik2026sampurner,
|
| 48 |
+
title={SampurNER: Fine-grained Named Entity Recognition Dataset for 22 Indian Languages},
|
| 49 |
+
author={Kaushik, Prachuryya and Anand, Ashish},
|
| 50 |
+
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
| 51 |
+
volume={40},
|
| 52 |
+
year={2026}
|
| 53 |
+
}
|