|
MARBERT is one of two models described in the paper ["ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic"](https://mageed.arts.ubc.ca/files/2020/12/marbert_arxiv_2020.pdf). MARBERT is a large-scale pre-trained masked language model focused on both Dialectal Arabic (DA) and MSA. Arabic has multiple varieties. To train MARBERT, we randomly sample 1B Arabic tweets from a large in-house dataset of about 6B tweets. We only include tweets with at least 3 Arabic words, based on character string matching, regardless whether the tweet has non-Arabic string or not. That is, we do not remove non-Arabic so long as the tweet meets the 3 Arabic word criterion. The dataset makes up 128GB of text (15.6B tokens). We use the same network architecture as ARBERT (BERT-base), but without the next sentence prediction (NSP) objective since tweets are short. See our [repo](https://github.com/UBC-NLP/LMBERT) for modifying BERT code to remove NSP. For more information about MARBERT, please visit our own GitHub [repo](https://github.com/UBC-NLP/marbert). |
