Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,6 @@ pretty_name: MultiCoNER2 English XLM-RoBERTa
|
|
| 20 |
|
| 21 |
**XLM-RoBERTa is fine-tuned on English [MultiCoNER2](https://huggingface.co/datasets/MultiCoNER/multiconer_v2) dataset for Fine-grained Named Entity Recognition.**
|
| 22 |
|
| 23 |
-
This model is part of the **AWED-FiNER** project, 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 |
The tagset of [MultiCoNER2](https://huggingface.co/datasets/MultiCoNER/multiconer_v2) is a fine-grained tagset. The fine to coarse level mapping of the tags are as follows:
|
| 26 |
|
| 27 |
* Location (LOC) : Facility, OtherLOC, HumanSettlement, Station
|
|
@@ -31,8 +29,6 @@ The tagset of [MultiCoNER2](https://huggingface.co/datasets/MultiCoNER/multicone
|
|
| 31 |
* Product (PROD) : Clothing, Vehicle, Food, Drink, OtherPROD
|
| 32 |
* Medical (MED) : Medication/Vaccine, MedicalProcedure, AnatomicalStructure, Symptom, Disease
|
| 33 |
|
| 34 |
-
[**AWED-FiNER collection**](https://huggingface.co/collections/prachuryyaIITG/awed-finer) | [**Paper**](https://huggingface.co/papers/2601.10161) | [**Agentic Tool**](https://github.com/PrachuryyaKaushik/AWED-FiNER) | [**Interactive Demo**](https://huggingface.co/spaces/prachuryyaIITG/AWED-FiNER)
|
| 35 |
-
|
| 36 |
## Model performance:
|
| 37 |
Precision: 78.29 <br>
|
| 38 |
Recall: 80.94 <br>
|
|
@@ -45,6 +41,8 @@ Learning Rate: 5e-5 <br>
|
|
| 45 |
Weight Decay: 0.01 <br>
|
| 46 |
Batch Size: 64 <br>
|
| 47 |
|
|
|
|
|
|
|
| 48 |
## Sample Usage of Agentic Tool
|
| 49 |
|
| 50 |
The AWED-FiNER agentic tool can be used to interact with expert models trained using this framework. Below is an example:
|
|
@@ -79,8 +77,8 @@ If you use this model, please cite the following papers:
|
|
| 79 |
year={2023}
|
| 80 |
}
|
| 81 |
|
| 82 |
-
@misc{
|
| 83 |
-
title={AWED-
|
| 84 |
author={Prachuryya Kaushik and Ashish Anand},
|
| 85 |
year={2026},
|
| 86 |
eprint={2601.10161},
|
|
|
|
| 20 |
|
| 21 |
**XLM-RoBERTa is fine-tuned on English [MultiCoNER2](https://huggingface.co/datasets/MultiCoNER/multiconer_v2) dataset for Fine-grained Named Entity Recognition.**
|
| 22 |
|
|
|
|
|
|
|
| 23 |
The tagset of [MultiCoNER2](https://huggingface.co/datasets/MultiCoNER/multiconer_v2) is a fine-grained tagset. The fine to coarse level mapping of the tags are as follows:
|
| 24 |
|
| 25 |
* Location (LOC) : Facility, OtherLOC, HumanSettlement, Station
|
|
|
|
| 29 |
* Product (PROD) : Clothing, Vehicle, Food, Drink, OtherPROD
|
| 30 |
* Medical (MED) : Medication/Vaccine, MedicalProcedure, AnatomicalStructure, Symptom, Disease
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Model performance:
|
| 33 |
Precision: 78.29 <br>
|
| 34 |
Recall: 80.94 <br>
|
|
|
|
| 41 |
Weight Decay: 0.01 <br>
|
| 42 |
Batch Size: 64 <br>
|
| 43 |
|
| 44 |
+
It is part of the [AWED-PIPER](https://github.com/PrachuryyaKaushik/AWED-PIPER) ecosystem: [**Paper**](https://huggingface.co/papers/2601.10161) | [**Agent for FgNER**](https://github.com/PrachuryyaKaushik/AWED-FiNER) | [**Web App for FgNER**](https://huggingface.co/spaces/prachuryyaIITG/AWED-FiNER) | [**Agent for PII Protection**](https://github.com/PrachuryyaKaushik/AWED-PIPER) | [**Web App for PII Protection**](https://huggingface.co/spaces/prachuryyaIITG/AWED_PII_Protector)
|
| 45 |
+
|
| 46 |
## Sample Usage of Agentic Tool
|
| 47 |
|
| 48 |
The AWED-FiNER agentic tool can be used to interact with expert models trained using this framework. Below is an example:
|
|
|
|
| 77 |
year={2023}
|
| 78 |
}
|
| 79 |
|
| 80 |
+
@misc{kaushik2026awedpiperagentswebapplications,
|
| 81 |
+
title={AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers},
|
| 82 |
author={Prachuryya Kaushik and Ashish Anand},
|
| 83 |
year={2026},
|
| 84 |
eprint={2601.10161},
|