metadata

language:
  - ca
license: apache-2.0
tags:
  - catalan
  - textual entailment
  - teca
  - CaText
  - Catalan Textual Corpus
datasets:
  - projecte-aina/teca
metrics:
  - accuracy
model-index:
  - name: roberta-base-ca-v2-cased-te
    results:
      - task:
          type: text-classification
        dataset:
          type: projecte-aina/teca
          name: TECA
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8342
widget:
  - text: M'agrades. T'estimo.
  - text: M'agrada el sol i la calor. A la Garrotxa plou molt.
  - text: El llibre va caure per la finestra. El llibre va sortir volant.
  - text: El meu aniversari és el 23 de maig. Faré anys a finals de maig.

Catalan BERTa-v2 (roberta-base-ca-v2) finetuned for Textual Entailment.

The roberta-base-ca-v2-cased-te is a Textual Entailment (TE) model for the Catalan language fine-tuned from the roberta-base-ca-v2 model, a RoBERTa base model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers (check the roberta-base-ca-v2 model card for more details).

Datasets

We used the TE dataset in Catalan called TECA for training and evaluation.

Evaluation and results

We evaluated the roberta-base-ca-cased-te on the TECA test set against standard multilingual and monolingual baselines:

Model	TECA (Accuracy)
roberta-base-ca-v2-cased-te	83.14
BERTa	79.26
mBERT	74.63
XLM-RoBERTa	33.30

For more details, check the fine-tuning and evaluation scripts in the official GitHub repository.

Citing

If you use any of these resources (datasets or models) in your work, please cite our latest paper:

@inproceedings{armengol-estape-etal-2021-multilingual,
    title = "Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? {A} Comprehensive Assessment for {C}atalan",
    author = "Armengol-Estap{\'e}, Jordi  and
      Carrino, Casimiro Pio  and
      Rodriguez-Penagos, Carlos  and
      de Gibert Bonet, Ona  and
      Armentano-Oller, Carme  and
      Gonzalez-Agirre, Aitor  and
      Melero, Maite  and
      Villegas, Marta",
    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-acl.437",
    doi = "10.18653/v1/2021.findings-acl.437",
    pages = "4933--4946",
}

Funding

This work was funded by the Catalan Government within the framework of the AINA project..