|
--- |
|
license: openrail |
|
language: |
|
- en |
|
- es |
|
- ro |
|
- fr |
|
--- |
|
|
|
# Fine-Tuned RoBERTa for Multilingual NER |
|
|
|
## Introduction |
|
|
|
This model is a fine-tuned version of the RoBERTa base model, specialized for Named Entity Recognition (NER) tasks in English, Spanish, French, and Romanian. |
|
|
|
## Capabilities |
|
|
|
The model is currently capable of recognizing: |
|
- Common names in English, Spanish, French, and Romanian |
|
- Most commonly used acronyms in these languages |
|
|
|
## Training Data |
|
|
|
The model was fine-tuned using the [`ner_acro_combined`](https://huggingface.co./datasets/eduardem/ner_acro_combined) dataset. |
|
|
|
## Usage |
|
|
|
This fine-tuned model is designed for: |
|
- Performing NER tasks in multilingual contexts |
|
- Identifying commonly used names and acronyms in the specified languages |
|
|
|
## Contributing |
|
|
|
If you have suggestions for improvements or bug reports related to this model, please feel free to open an issue or submit a pull request. |
|
|
|
|