---
language: 
- multilingual
- grc
- en
- la
license: apache-2.0
inference: false
---
# PhilBerta

The paper [Exploring Language Models for Classical Philology](https://todo.com) is the first effort to systematically provide state-of-the-art language models for Classical Philology. PhilBerta is a RoBerta-base sized, multilingual, encoder-only variant.  

This model was trained using data from the [Open Greek & Latin Project](https://opengreekandlatin.org/), the CLARIN corpus [Greek Medieval Texts](https://inventory.clarin.gr/corpus/890), the [Patrologia Graeca](https://patristica.net/graeca/), the [Corpus Corporum](https://mlat.uzh.ch/), and [Project Gutenberg](https://www.gutenberg.org/).

Further information can be found in our paper or in our [GitHub repository](https://github.com/Heidelberg-NLP/ancient-language-models).

## Usage
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained('bowphs/PhilBerta')
model = AutoModelForMaskedLM.from_pretrained('bowphs/PhilBerta')
```
Please check out the awesome Hugging Face tutorials on how to fine-tune our models.

## Evaluation Results
When fine-tuned on data from [Universal Dependencies 2.10](https://universaldependencies.org/), PhilBerta achieves the following results on the Ancient Greek Perseus dataset:

| Task | XPoS | UPoS  | UAS | LAS |
|:--:|:--:|:--:|:--:|:--:|
|      |95.60|90.41|86.99|82.69|

When fine-tuned on PoS data from [EvaLatin 2022](https://universaldependencies.org/), it achieves the following results:

| Task | Classical | Cross-genre  | Cross-time | 
|:--:|:--:|:--:|:--:|
|      |98.23|96.59|93.25|

## Contact
If you have any questions or problems, feel free to [reach out](mailto:riemenschneider@cl.uni-heidelberg.de).

## Citation
```bibtex
@incollection{riemenschneiderfrank:2023,
    address = "Toronto, Canada",
    author = "Riemenschneider, Frederick and Frank, Anette",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23)",
    note = "to appear",
    pubType = "incollection",
    publisher = "Association for Computational Linguistics",
    title = "Exploring Large Language Models for Classical Philology",
    url = "https://arxiv.org/abs/2305.13698",
    year = "2023",
    key = "riemenschneiderfrank:2023"
}
```