Edit model card

RoBERTa Turkish medium Morph-level 7k (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 7.5k.

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}
}
Downloads last month
3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train ctoraman/RoBERTa-TR-medium-morph-7k