Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,56 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- jv
|
5 |
+
datasets:
|
6 |
+
- JavaneseHonorifics/Unggah-Ungguh
|
7 |
+
base_model:
|
8 |
+
- w11wo/javanese-distilbert-small-imdb
|
9 |
+
pipeline_tag: text-classification
|
10 |
+
library_name: transformers
|
11 |
+
---
|
12 |
+
# Unggah-Ungguh-Javanese-Distilbert-Classifier
|
13 |
+
|
14 |
+
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!
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
- **Model type**: A classifier model trained on a highly curated Unggah-Ungguh dataset that represent Javanese Honorific rules and systems.
|
18 |
+
- **Language(s) NLP**: Javanese
|
19 |
+
- **License:** CC-BY-NC 4.0
|
20 |
+
- **Finetuned from model:** w11wo/javanese-distilbert-small-imdb
|
21 |
+
|
22 |
+
## Model Sources
|
23 |
+
|
24 |
+
- **Project Page:** https://javanesehonorifics.github.io/
|
25 |
+
- **Repository:** https://github.com/JavaneseHonorifics
|
26 |
+
- **Paper:** https://arxiv.org/abs/2502.20864
|
27 |
+
|
28 |
+
## Using the model
|
29 |
+
```python
|
30 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
31 |
+
import torch
|
32 |
+
model_path = "JavaneseHonorifics/Unggah-Ungguh-Javanese-Distilbert-Classifier"
|
33 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
34 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_path)
|
35 |
+
INPUT_TEXT = "Mbak Srini mangan pecel ajange pincuk"
|
36 |
+
tokenized_input = tokenizer([INPUT_TEXT], return_tensors="pt", truncation=True, padding=True)
|
37 |
+
with torch.no_grad():
|
38 |
+
outputs = model(**tokenized_input)
|
39 |
+
y_pred = outputs.logits.argmax(-1)
|
40 |
+
print("Predicted class:", y_pred.item())
|
41 |
+
```
|
42 |
+
|
43 |
+
## License and Use
|
44 |
+
|
45 |
+
Unggah-Ungguh is licensed under the CC-BY-NC 4.0
|
46 |
+
|
47 |
+
## Citation
|
48 |
+
|
49 |
+
```bibtex
|
50 |
+
@article{farhansyah2025language,
|
51 |
+
title={Do Language Models Understand Honorific Systems in Javanese?},
|
52 |
+
author={Farhansyah, Mohammad Rifqi and Darmawan, Iwan and Kusumawardhana, Adryan and Winata, Genta Indra and Aji, Alham Fikri and Wijaya, Derry Tanti},
|
53 |
+
journal={arXiv preprint arXiv:2502.20864},
|
54 |
+
year={2025}
|
55 |
+
}
|
56 |
+
```
|