xlm-roberta-base-focus-arabic

XLM-R adapted to Arabic using "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models".

Code: https://github.com/konstantinjdobler/focus

Paper: https://arxiv.org/abs/2305.14481

Usage

from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("konstantindobler/xlm-roberta-base-focus-arabic")
model = AutoModelForMaskedLM.from_pretrained("konstantindobler/xlm-roberta-base-focus-arabic")

# Use model and tokenizer as usual

Details

The model is based on xlm-roberta-base and was adapted to Arabic. The original multilingual tokenizer was replaced by a language-specific Arabic tokenizer with a vocabulary of 50k tokens. The new embeddings were initialized with FOCUS. The model was then trained on data from CC100 for 390k optimizer steps. More details and hyperparameters can be found in the paper.

Disclaimer

The web-scale dataset used for pretraining and tokenizer training (CC100) might contain personal and sensitive information. Such behavior needs to be assessed carefully before any real-world deployment of the models. Also, the tokenizer training was conducted using a sentencepiece character_coverage of 100%. As a result, the vocabulary contains characters which are usually not used in Arabic.

Citation

Please cite FOCUS as follows:

@misc{dobler-demelo-2023-focus,
    title={FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models},
    author={Konstantin Dobler and Gerard de Melo},
    year={2023},
    eprint={2305.14481},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}