Roberta Large Bne Sqac

🚀 Spanish RoBERTa-large trained on BNE finetuned for Spanish Question Answering Corpus (SQAC) dataset.

This model is a Spanish Question Answering (QA) model fine - tuned from a pre - trained RoBERTa large model. It is trained on the BNE and finetuned for the SQAC dataset, aiming to provide high - quality question - answering services for the Spanish language.

🚀 Quick Start

from transformers import pipeline
nlp = pipeline("question - answering", model="PlanTL - GOB - ES/roberta - large - bne - sqac")
text = "¿Dónde vivo?"
context = "Me llamo Wolfgang y vivo en Berlin"
  
qa_results = nlp(text, context)
print(qa_results)

✨ Features

• Language - specific: Specifically designed for the Spanish language, leveraging a large - scale Spanish corpus for pre - training.
• Fine - tuned for QA: Fine - tuned on the SQAC dataset, making it suitable for extractive question - answering tasks in Spanish.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline
nlp = pipeline("question - answering", model="PlanTL - GOB - ES/roberta - large - bne - sqac")
text = "¿Dónde vivo?"
context = "Me llamo Wolfgang y vivo en Berlin"
  
qa_results = nlp(text, context)
print(qa_results)

📚 Documentation

Model description

The roberta - large - bne - sqac is a Question Answering (QA) model for the Spanish language fine - tuned from the [roberta - large - bne](https://huggingface.co/PlanTL - GOB - ES/roberta - large - bne) model. The [roberta - large - bne](https://huggingface.co/PlanTL - GOB - ES/roberta - large - bne) is a RoBERTa large model pre - trained using the largest Spanish corpus known to date, with a total of 570GB of clean and deduplicated text, processed for this work, compiled from the web crawlings performed by the National Library of Spain (Biblioteca Nacional de España) from 2009 to 2019.

Intended uses and limitations

The roberta - large - bne - sqac model can be used for extractive question answering. However, the model is limited by its training dataset and may not generalize well for all use cases.

Limitations and bias

At the time of submission, no measures have been taken to estimate the bias embedded in the model. However, we are well aware that our models may be biased since the corpora have been collected using crawling techniques on multiple web sources. We intend to conduct research in these areas in the future, and if completed, this model card will be updated.

Training

Training data

We used the QA dataset in Spanish called [SQAC corpus](https://huggingface.co/datasets/PlanTL - GOB - ES/SQAC) for training and evaluation.

Training procedure

The model was trained with a batch size of 16 and a learning rate of 1e - 5 for 5 epochs. We then selected the best checkpoint using the downstream task metric in the corresponding development set and then evaluated it on the test set.

Evaluation

Evaluation results

We evaluated the roberta - large - bne - sqac on the SQAC test set against standard multilingual and monolingual baselines:

For more details, check the fine - tuning and evaluation scripts in the official [GitHub repository](https://github.com/PlanTL - GOB - ES/lm - spanish).

Additional information

Author

Text Mining Unit (TeMU) at the Barcelona Supercomputing Center (bsc - temu@bsc.es)

Contact information

For further information, send an email to <plantl - gob - es@bsc.es>

Copyright

Copyright by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) (2022)

Licensing information

[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE - 2.0)

Funding

This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan - TL.

Citing information

If you use this model, please cite our paper:

@article{,
   abstract = {We want to thank the National Library of Spain for such a large effort on the data gathering and the Future of Computing Center, a
Barcelona Supercomputing Center and IBM initiative (2020). This work was funded by the Spanish State Secretariat for Digitalization and Artificial
Intelligence (SEDIA) within the framework of the Plan - TL.},
   author = {Asier Gutiérrez Fandiño and Jordi Armengol Estapé and Marc Pàmies and Joan Llop Palao and Joaquin Silveira Ocampo and Casimiro Pio Carrino and Carme Armentano Oller and Carlos Rodriguez Penagos and Aitor Gonzalez Agirre and Marta Villegas},
   doi = {10.26342/2022 - 68 - 3},
   issn = {1135 - 5948},
   journal = {Procesamiento del Lenguaje Natural},
   keywords = {Artificial intelligence,Benchmarking,Data processing.,MarIA,Natural language processing,Spanish language modelling,Spanish language resources,Tractament del llenguatge natural (Informàtica),Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural},
   publisher = {Sociedad Española para el Procesamiento del Lenguaje Natural},
   title = {MarIA: Spanish Language Models},
   volume = {68},
   url = {https://upcommons.upc.edu/handle/2117/367156#.YyMTB4X9A - 0.mendeley},
   year = {2022},
}

Disclaimer

The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions.

When third parties deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of artificial intelligence.

In no event shall the owner of the models (SEDIA – State Secretariat for digitalization and artificial intelligence) nor the creator (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models.

🔧 Technical Details

Model Information

Metrics

The model is evaluated using metrics such as F1 and exact match. The F1 score on the SQAC test set is 0.8202.

📄 License

This project is licensed under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE - 2.0).