RoBERTa-ceb-cased / README.md
GuyCalledMav's picture
Create README.md
1632a9f
|
raw
history blame
1.39 kB
metadata
language:
  - tl
tags:
  - RoBERTa
  - Tagalog
  - Taglish

Model Description

As part of the ITANONG project's 10 billion-token Tagalog dataset, we have introduced our initial pre-trained language models for Philippine languages. Our model suite encompasses various BERT-based, GPT-based, and Sentence Transformers tailored for Tagalog,Taglish and Cebuano.

Training Details

This model was trained using an Nvidia V100-32GB GPU on DOST-ASTI Computing and Archiving Research Environment (COARE) - https://asti.dost.gov.ph/projects/coare/

Training Data

The training dataset was compiled from both formal and informal sources, consisting of 194,001 instances from formal channels and 1,816,735 from informal sources. More information on pre-processing and training parameters on our paper

Citation

Paper : iTANONG-DS : A Collection of Benchmark Datasets for Downstream Natural Language Processing Tasks on Select Philippine Language

Bibtex:

@inproceedings{2023itanongds,
  title={{iTANONG-DS: A Collection of Benchmark Datasets for Downstream Natural Language Processing Tasks on Select Philippine Languages}},
  author={Visperas, M. and Borjal, C. J. and Adoptante, A. J. and Peramo, E. and Abacial, D. S. and Decano, M. M.},
  booktitle={2023 International Conference on Natural Language and Speech Processing},
  year={2023},
  address={Trento, Italy},
  
}