metadata
language:
- tr
tags:
- roberta
license: cc-by-nc-sa-4.0
datasets:
- oscar
RoBERTa Turkish medium Morph-level 66k (uncased)
Pretrained model on Turkish language using a masked language modeling (MLM) objective. The model is uncased. The pretrained corpus is OSCAR's Turkish split, but it is further filtered and cleaned.
Model architecture is similar to bert-medium (8 layers, 8 heads, and 512 hidden size). Tokenization algorithm is Morph-level, which means that text is split according to a Turkish morphological analyzer (Zemberek). Vocabulary size is 64.2k.
Note that this model needs a preprocessing step before running, because the tokenizer file is not a morphological anaylzer. That is, the test dataset can not be split into morphemes with the tokenizer file. The user needs to process any test dataset by a Turkish morphological analyzer (Zemberek in this case) before running evaluation.
The details and performance comparisons can be found at this paper: https://arxiv.org/abs/2204.08832
The following code can be used for model loading and tokenization, example max length (514) can be changed:
model = AutoModel.from_pretrained([model_path])
#for sequence classification:
#model = AutoModelForSequenceClassification.from_pretrained([model_path], num_labels=[num_classes])
tokenizer = PreTrainedTokenizerFast(tokenizer_file=[file_path])
tokenizer.mask_token = "[MASK]"
tokenizer.cls_token = "[CLS]"
tokenizer.sep_token = "[SEP]"
tokenizer.pad_token = "[PAD]"
tokenizer.unk_token = "[UNK]"
tokenizer.bos_token = "[CLS]"
tokenizer.eos_token = "[SEP]"
tokenizer.model_max_length = 514
BibTeX entry and citation info
@misc{https://doi.org/10.48550/arxiv.2204.08832,
doi = {10.48550/ARXIV.2204.08832},
url = {https://arxiv.org/abs/2204.08832},
author = {Toraman, Cagri and Yilmaz, Eyup Halit and Şahinuç, Furkan and Ozcelik, Oguzhan},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Impact of Tokenization on Language Models: An Analysis for Turkish},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}