Commit ·
a299453
1
Parent(s): 5fa6883
Improve model card: add library_name, update paper link and GitHub link (#1)
Browse files- Improve model card: add library_name, update paper link and GitHub link (146a124f11a97f3aac980ae18e296a5ce8240a11)
Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,28 +1,30 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
language:
|
| 4 |
-
- ne
|
| 5 |
base_model:
|
| 6 |
- google/muril-large-cased
|
| 7 |
-
pipeline_tag: token-classification
|
| 8 |
-
tags:
|
| 9 |
-
- NER
|
| 10 |
-
- Named_Entity_Recognition
|
| 11 |
-
pretty_name: SampurNER Nepali MuRIL
|
| 12 |
datasets:
|
| 13 |
- prachuryyaIITG/SampurNER
|
|
|
|
|
|
|
|
|
|
| 14 |
metrics:
|
| 15 |
- f1
|
| 16 |
- precision
|
| 17 |
- recall
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
**MuRIL is fine-tuned on Nepali [SampurNER](https://huggingface.co/datasets/prachuryyaIITG/SampurNER) dataset for Fine-grained Named Entity Recognition. It is created using the [EaMaTa](https://github.com/PrachuryyaKaushik/SampurNER/blob/main/SampurNER_AAAI_extended.pdf) framework, utilizing the [Few-NERD](https://huggingface.co/datasets/DFKI-SLT/few-nerd) dataset.** <br>
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
SampurNER Dataset: [datasets/prachuryyaIITG/SampurNER](https://huggingface.co/datasets/prachuryyaIITG/SampurNER)
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
The tagset of [Few-NERD](https://aclanthology.org/2021.acl-long.248.pdf) is a fine-grained tagset. The fine to coarse level mapping of the tags are as follows:
|
| 28 |
|
|
@@ -80,14 +82,6 @@ print(result)
|
|
| 80 |
If you use this model, please cite the following papers:
|
| 81 |
|
| 82 |
```bibtex
|
| 83 |
-
@inproceedings{kaushik2026sampurner,
|
| 84 |
-
title={SampurNER: Fine-grained Named Entity Recognition Dataset for 22 Indian Languages},
|
| 85 |
-
author={Kaushik, Prachuryya and Anand, Ashish},
|
| 86 |
-
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
| 87 |
-
volume={40},
|
| 88 |
-
year={2026}
|
| 89 |
-
}
|
| 90 |
-
|
| 91 |
@misc{kaushik2026awedfineragentswebapplications,
|
| 92 |
title={AWED-FiNER: Agents, Web applications, and Expert Detectors for Fine-grained Named Entity Recognition across 36 Languages for 6.6 Billion Speakers},
|
| 93 |
author={Prachuryya Kaushik and Ashish Anand},
|
|
@@ -98,6 +92,14 @@ If you use this model, please cite the following papers:
|
|
| 98 |
url={https://arxiv.org/abs/2601.10161},
|
| 99 |
}
|
| 100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
@inproceedings{ding-etal-2021-nerd,
|
| 102 |
title = "Few-{NERD}: A Few-shot Named Entity Recognition Dataset",
|
| 103 |
author = "Ding, Ning and Xu, Guangwei and Chen, Yulin and Wang, Xiaobin and Han, Xu and Xie, Pengjun and Zheng, Haitao and Liu, Zhiyuan",
|
|
@@ -109,3 +111,4 @@ If you use this model, please cite the following papers:
|
|
| 109 |
doi = "10.18653/v1/2021.acl-long.248",
|
| 110 |
pages = "3198--3213",
|
| 111 |
}
|
|
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- google/muril-large-cased
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
datasets:
|
| 5 |
- prachuryyaIITG/SampurNER
|
| 6 |
+
language:
|
| 7 |
+
- ne
|
| 8 |
+
license: mit
|
| 9 |
metrics:
|
| 10 |
- f1
|
| 11 |
- precision
|
| 12 |
- recall
|
| 13 |
+
pipeline_tag: token-classification
|
| 14 |
+
tags:
|
| 15 |
+
- NER
|
| 16 |
+
- Named_Entity_Recognition
|
| 17 |
+
pretty_name: SampurNER Nepali MuRIL
|
| 18 |
+
library_name: transformers
|
| 19 |
---
|
| 20 |
|
| 21 |
**MuRIL is fine-tuned on Nepali [SampurNER](https://huggingface.co/datasets/prachuryyaIITG/SampurNER) dataset for Fine-grained Named Entity Recognition. It is created using the [EaMaTa](https://github.com/PrachuryyaKaushik/SampurNER/blob/main/SampurNER_AAAI_extended.pdf) framework, utilizing the [Few-NERD](https://huggingface.co/datasets/DFKI-SLT/few-nerd) dataset.** <br>
|
| 22 |
|
| 23 |
+
This model is part of the work presented in the paper [AWED-FiNER: Agents, Web applications, and Expert Detectors for Fine-grained Named Entity Recognition across 36 Languages for 6.6 Billion Speakers](https://huggingface.co/papers/2601.10161).
|
|
|
|
|
|
|
| 24 |
|
| 25 |
+
- **Code:** [https://github.com/PrachuryyaKaushik/AWED-FiNER](https://github.com/PrachuryyaKaushik/AWED-FiNER)
|
| 26 |
+
- **Interactive Demo:** [https://huggingface.co/spaces/prachuryyaIITG/AWED-FiNER](https://huggingface.co/spaces/prachuryyaIITG/AWED-FiNER)
|
| 27 |
+
- **Dataset:** [prachuryyaIITG/SampurNER](https://huggingface.co/datasets/prachuryyaIITG/SampurNER)
|
| 28 |
|
| 29 |
The tagset of [Few-NERD](https://aclanthology.org/2021.acl-long.248.pdf) is a fine-grained tagset. The fine to coarse level mapping of the tags are as follows:
|
| 30 |
|
|
|
|
| 82 |
If you use this model, please cite the following papers:
|
| 83 |
|
| 84 |
```bibtex
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
@misc{kaushik2026awedfineragentswebapplications,
|
| 86 |
title={AWED-FiNER: Agents, Web applications, and Expert Detectors for Fine-grained Named Entity Recognition across 36 Languages for 6.6 Billion Speakers},
|
| 87 |
author={Prachuryya Kaushik and Ashish Anand},
|
|
|
|
| 92 |
url={https://arxiv.org/abs/2601.10161},
|
| 93 |
}
|
| 94 |
|
| 95 |
+
@inproceedings{kaushik2026sampurner,
|
| 96 |
+
title={SampurNER: Fine-grained Named Entity Recognition Dataset for 22 Indian Languages},
|
| 97 |
+
author={Kaushik, Prachuryya and Anand, Ashish},
|
| 98 |
+
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
| 99 |
+
volume={40},
|
| 100 |
+
year={2026}
|
| 101 |
+
}
|
| 102 |
+
|
| 103 |
@inproceedings{ding-etal-2021-nerd,
|
| 104 |
title = "Few-{NERD}: A Few-shot Named Entity Recognition Dataset",
|
| 105 |
author = "Ding, Ning and Xu, Guangwei and Chen, Yulin and Wang, Xiaobin and Han, Xu and Xie, Pengjun and Zheng, Haitao and Liu, Zhiyuan",
|
|
|
|
| 111 |
doi = "10.18653/v1/2021.acl-long.248",
|
| 112 |
pages = "3198--3213",
|
| 113 |
}
|
| 114 |
+
```
|