| language: | |
| - sl | |
| - en | |
| - multilingual | |
| licence: cc-by-sa-4.0 | |
| # SlEng-bert | |
| SlEng-bert is a bilingual, Slovene-English masked language model. | |
| SlEng-bert was trained from scratch on Slovene and English, conversational, non-standard, and slang language. | |
| The model has 12 transformer layers, and is roughly equal in size to BERT and RoBERTa base models. The pre-training task used was masked language modeling, with no other tasks (like NSP). | |
| The tokenizer and corpora used to train SlEng-bert were also used for training the [SloBERTa-SlEng](https://huggingface.co/cjvt/sloberta-sleng) model. | |
| The difference between the two is: SlEng-bert was trained from scratch for 40 epochs; SloBERTa-SlEng is SloBERTa further pre-trained for 2 epochs on new corpora. | |
| ## Training corpora | |
| The model was trained on English and Slovene tweets, Slovene corpora [MaCoCu](http://hdl.handle.net/11356/1517) and [Frenk](http://hdl.handle.net/11356/1201), | |
| and a small subset of English [Oscar](https://huggingface.co/datasets/oscar) corpus. We tried to keep the sizes of English and Slovene corpora as equal as possible. | |
| Training corpora had in total about 2.7 billion words. | |