---
license: cc-by-nc-4.0
language:
- jv
datasets:
- JavaneseHonorifics/Unggah-Ungguh
base_model:
- w11wo/javanese-distilbert-small-imdb
pipeline_tag: text-classification
library_name: transformers
---
# Unggah-Ungguh-Javanese-Distilbert-Classifier

Unggah-Ungguh-Javanese-Distilbert-Classifier is part of the Unggah-Ungguh's model family, a classifier model for Javanese Honorific Classification task that was mentioned in "Do Language Models Understand Honorific Systems in Javanese?". Check out [our paper](https://arxiv.org/abs/2502.20864) for more information!

## Model description
- **Model type**: A classifier model trained on a highly curated Unggah-Ungguh dataset that represent Javanese Honorific rules and systems.
- **Language(s) NLP**: Javanese
- **License:** CC-BY-NC 4.0
- **Finetuned from model:** w11wo/javanese-distilbert-small-imdb

## Model Sources

- **Project Page:** https://javanesehonorifics.github.io/
- **Repository:** https://github.com/JavaneseHonorifics
- **Paper:** https://arxiv.org/abs/2502.20864

## Using the model
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model_path = "JavaneseHonorifics/Unggah-Ungguh-Javanese-Distilbert-Classifier"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)
INPUT_TEXT = "Mbak Srini mangan pecel ajange pincuk"
tokenized_input = tokenizer([INPUT_TEXT], return_tensors="pt", truncation=True, padding=True)
with torch.no_grad():
    outputs = model(**tokenized_input)
    y_pred = outputs.logits.argmax(-1)
print("Predicted class:", y_pred.item())
```

## License and Use

Unggah-Ungguh is licensed under the CC-BY-NC 4.0

## Citation

```bibtex
@article{farhansyah2025language,
  title={Do Language Models Understand Honorific Systems in Javanese?},
  author={Farhansyah, Mohammad Rifqi and Darmawan, Iwan and Kusumawardhana, Adryan and Winata, Genta Indra and Aji, Alham Fikri and Wijaya, Derry Tanti},
  journal={arXiv preprint arXiv:2502.20864},
  year={2025}
}
```