language:
- ca
license: apache-2.0
tags:
- catalan
- paraphrase
- text-classification
- multi-class-classification
- natural-language-understanding
- intent-classificaiton
datasets:
- AmazonScience/massive
metrics:
- f1
model-index:
- name: roberta-base-ca-v2-massive
results:
- task:
name: text-classification
type: text-classification
dataset:
name: MASSIVE
type: AmazonScience/massive
config: ca-ES
split: test
metrics:
- name: F1
type: f1
value: 0.8732
widget:
- text: m'agraden les cançons del serrat
- text: quina hora és
- text: què hi ha de nou a les notícies
- text: quins errors sols fer
Catalan BERTa (roberta-large-ca-v2) finetuned for Intent Classification
Table of Contents
Click to expand
Model description
The roberta-base-ca-v2-massive is a Intent Classificaiton model for the Catalan language fine-tuned from the roberta-large-ca-v2 model, a RoBERTa base model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers.
Intended uses and limitations
The roberta-base-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-base-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 5e-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-base-ca-v2-massive on the MASSIVE test set obtaining a weighted F1 score of 87.32.
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 aina@bsc.es
Copyright
Copyright (c) 2022 Text Mining Unit at Barcelona Supercomputing Center
Licensing information
Funding
This work was funded by the Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya within the framework of Projecte AINA.
Citation Information
NA
Disclaimer
Click to expand
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.