PhilTa
The paper Exploring Language Models for Classical Philology is the first effort to systematically provide state-of-the-art language models for Classical Philology. PhilTa is a T5-base sized, multilingual, encoder-decoder variant.
This model was trained using data from the Open Greek & Latin Project, the CLARIN corpus Greek Medieval Texts, the Patrologia Graeca, the Corpus Corporum, and Project Gutenberg.
Further information can be found in our paper or in our GitHub repository.
Usage
from transformers import AutoTokenizer, AutoModelForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained('bowphs/PhilTa')
model = AutoModelForConditionalGeneration.from_pretrained('bowphs/PhilTa')
Please check out the awesome Hugging Face tutorials on how to fine-tune our models.
Evaluation Results
When fine-tuned on lemmatization data from EvaLatin 2022, PhilTa achieves the following results:
Task | Classical | Cross-genre | Cross-time |
---|---|---|---|
97.33 | 93.40 | 91.91 |
PhilTa is especially strong when more than one of the three languages should be processed.
Contact
If you have any questions or problems, feel free to reach out.
Citation
@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"
}
- Downloads last month
- 20