roberta-large-ca-v2-massive

Catalan BERTa (roberta-large-ca-v2) finetuned for Intent Classification

Table of Contents

<details> <summary>Click to expand</summary>

• Model description
• Intended uses and limitations
• How to use
• Limitations and bias
• Training
  • Training data
  • Training procedure
• Evaluation
  • Variable and metrics
  • Evaluation results
• Additional information
  • Author
  • Contact information
  • Copyright
  • Licensing information
  • Funding
  • Citing information
  • Disclaimer

</details>

Model description

The roberta-large-ca-v2-massive is a Intent Classification model for the Catalan language fine-tuned from the roberta-large-ca-v2 model, a RoBERTa large model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers.

The model uses MASSIVE 1.1, a parallel dataset of > 1M utterances across 52 languages with annotations for the Natural Language Understanding tasks of intent prediction and slot annotation. Utterances span 60 intents and include 55 slot types.

Intended uses and limitations

The roberta-large-ca-v2-massive model can be used for intent prediction in plain text sentences. It can be used in combination with an Automatic Speech Recognition model in order to implement a Voice Assistant. The model is limited by its training dataset and may not generalize well for all use cases.

How to use

Here is how to use this model:

from transformers import pipeline
from pprint import pprint

nlp = pipeline("text-classification", model="projecte-aina/roberta-large-ca-v2-massive")
example = "m'agraden les cançons del serrat"

intent = nlp(example)
pprint(intent)

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 Catalan split of the MASSIVE dataset for training and evaluation.

Training procedure

The model was trained with a batch size of 16 and a learning rate of 1e-5 for 20 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

Variable and metrics

This model was finetuned maximizing the weighted F1 score.

Evaluation results

We evaluated the roberta-large-ca-v2-massive on the MASSIVE test set obtaining a weighted F1 score of 87.56.

Additional information

Author

Text Mining Unit (TeMU) at the Barcelona Supercomputing Center ([email protected])

Contact information

For further information, send an email to [email protected]

Copyright

Copyright (c) 2022 Text Mining Unit at Barcelona Supercomputing Center

Licensing information

Apache License, Version 2.0

Funding

This work was funded by the [Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya](https://politiquesdigitals.gencat.cat/ca/inici/index.html#googtrans(ca|en) within the framework of Projecte AINA.

Citation Information

NA

Disclaimer

<details> <summary>Click to expand</summary>

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 and creator of the models (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models.