Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,73 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- google/muril-large-cased
|
| 7 |
+
pipeline_tag: token-classification
|
| 8 |
+
tags:
|
| 9 |
+
- NER
|
| 10 |
+
- Named_Entity_Recognition
|
| 11 |
+
pretty_name: FewNERD EnglishBishnupriya MuRIL
|
| 12 |
+
datasets:
|
| 13 |
+
- DFKI-SLT/few-nerd
|
| 14 |
+
metrics:
|
| 15 |
+
- f1
|
| 16 |
+
- precision
|
| 17 |
+
- recall
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
**MuRIL is fine-tuned on English [Few-NERD](https://huggingface.co/datasets/DFKI-SLT/few-nerd) dataset.** <br>
|
| 21 |
+
|
| 22 |
+
Read the papers: [FewNERD in ACL](https://aclanthology.org/2021.acl-long.248.pdf) , [SampurNER in AAAI-2026](https://github.com/PrachuryyaKaushik/SampurNER/blob/main/SampurNER_AAAI_extended.pdf)
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
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:
|
| 26 |
+
|
| 27 |
+
* Location : GPE, Body of Water, Island, Mountain, Park, Road/Transit, Other
|
| 28 |
+
* Person : Actor, Artist/Author, Athlete, Director, Politician, Scholar, Soldier, Other
|
| 29 |
+
* ORG : Company, Education, Government, Media, Political Party, Religion, Sports League, Show Organization, Other
|
| 30 |
+
* Building : Airport, Hospital, Hotel, Library, Restaurant, Sports Facility, Theater, Other
|
| 31 |
+
* Art : Music, Film, Written Art, Broadcast, Painting, Other
|
| 32 |
+
* Product : Airplane, Car, Food, Game, Ship, Software, Train, Weapon, Other
|
| 33 |
+
* Event : Attack, Election, Natural Disaster, Protest, Sports Event, Other
|
| 34 |
+
* Misc : Astronomy, Award, Biology, Chemistry, Currency, Disease, Educational Degree, God, Language, Law, Living Thing, Medical
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
## Model performance:
|
| 38 |
+
Precision: 66.21 <br>
|
| 39 |
+
Recall: 69.98 <br>
|
| 40 |
+
**F1: 68.04** <br>
|
| 41 |
+
|
| 42 |
+
## Training Parameters:
|
| 43 |
+
Epochs: 6 <br>
|
| 44 |
+
Optimizer: AdamW <br>
|
| 45 |
+
Learning Rate: 5e-5 <br>
|
| 46 |
+
Weight Decay: 0.01 <br>
|
| 47 |
+
Batch Size: 64 <br>
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
## Citation
|
| 51 |
+
|
| 52 |
+
If you use this model, please cite the following papers:
|
| 53 |
+
|
| 54 |
+
```bibtex
|
| 55 |
+
@inproceedings{ding-etal-2021-nerd,
|
| 56 |
+
title = "Few-{NERD}: A Few-shot Named Entity Recognition Dataset",
|
| 57 |
+
author = "Ding, Ning and Xu, Guangwei and Chen, Yulin and Wang, Xiaobin and Han, Xu and Xie, Pengjun and Zheng, Haitao and Liu, Zhiyuan",
|
| 58 |
+
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
|
| 59 |
+
month = aug,
|
| 60 |
+
year = "2021",
|
| 61 |
+
publisher = "Association for Computational Linguistics",
|
| 62 |
+
url = "https://aclanthology.org/2021.acl-long.248",
|
| 63 |
+
doi = "10.18653/v1/2021.acl-long.248",
|
| 64 |
+
pages = "3198--3213",
|
| 65 |
+
}
|
| 66 |
+
|
| 67 |
+
@inproceedings{kaushik2026sampurner,
|
| 68 |
+
title={SampurNER: Fine-grained Named Entity Recognition Dataset for 22 Indian Languages},
|
| 69 |
+
author={Kaushik, Prachuryya and Anand, Ashish},
|
| 70 |
+
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
| 71 |
+
volume={40},
|
| 72 |
+
year={2026}
|
| 73 |
+
}
|