---
language:
- egy
- de
tags:
- translation
- ancient-egyptian
- hieroglyphics
- contamination-study
- nlp4dh
license: mit
base_model: facebook/mbart-large-50-many-to-many-mmt
pipeline_tag: translation
---

# mBART-50 — Hieroglyphic-to-German Translation

This model is part of the paper **"Data Contamination in Neural Machine Translation of Ancient Egyptian Hieroglyphics"** (NLP4DH 2026).

## Model Description

mBART-50 (611M) fine-tuned for cross-architecture validation (lr=3e-5, AdamW, cosine warmup, 3x A6000 GPUs). Best checkpoint at step 2,000.

**Task:** Ancient Egyptian hieroglyphics (Gardiner notation) → German translation

## Performance

| Subset | BLEU |
|--------|------|
| All (n=50) | 42.5 |
| Contaminated (n=16) | 72.8 |
| Clean (n=34) | 35.5 |

> **Important:** The "All" and "Contaminated" BLEU scores are inflated due to target-side data contamination (32% of test targets appear in training). The **Clean** score represents genuine translation quality on decontaminated samples.

## Usage

```python
from transformers import M2MForConditionalGeneration, M2MTokenizer

model = M2MForConditionalGeneration.from_pretrained("bumblelbee/hiero-mbart50")
tokenizer = M2MTokenizer.from_pretrained("bumblelbee/hiero-mbart50")

# Gardiner notation input (hieroglyphic transliteration)
source = "D36 N35 G17 D21 X1 O34"

tokenizer.src_lang = "ea"
inputs = tokenizer(source, return_tensors="pt")
generated = model.generate(**inputs, forced_bos_token_id=tokenizer.get_lang_id("de"))
output = tokenizer.decode(generated[0], skip_special_tokens=True)
print(output)
```

## Training Data

Fine-tuned on 18,669 ea→de pairs from the Thesaurus Linguae Aegyptiae (TLA), maintained by the Berlin-Brandenburg Academy of Sciences and Humanities.

## Citation

```bibtex
@inproceedings{toutou-etal-2026-data,
  title     = {Data Contamination in Neural Hieroglyphic Translation:
               A Reproducibility Study},
  author    = {Toutou, Ammar and Harb, Abdelrahman and Basta, Christine},
  booktitle = {Proceedings of the 6th International Conference on
               Natural Language Processing for Digital Humanities
               (NLP4DH 2026)},
  year      = {2026},
  address   = {San Diego, USA},
  publisher = {Association for Computational Linguistics},
}
```

## Paper Repository

See the full paper, scripts, and results: [GitHub repository](https://github.com/[repository])