Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.20111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915413499052032 |
|---|---|
| author | Alva, Rodrigo Gabriel Salazar Nuñez, Matías López, Cristian Arista, Javier Martín |
| author_facet | Alva, Rodrigo Gabriel Salazar Nuñez, Matías López, Cristian Arista, Javier Martín |
| contents | Preserving ancient languages is essential for understanding humanity's cultural and linguistic heritage, yet Old English remains critically under-resourced, limiting its accessibility to modern natural language processing (NLP) techniques. We present a scalable framework that uses advanced large language models (LLMs) to generate high-quality Old English texts, addressing this gap. Our approach combines parameter-efficient fine-tuning (Low-Rank Adaptation, LoRA), data augmentation via backtranslation, and a dual-agent pipeline that separates the tasks of content generation (in English) and translation (into Old English). Evaluation with automated metrics (BLEU, METEOR, and CHRF) shows significant improvements over baseline models, with BLEU scores increasing from 26 to over 65 for English-to-Old English translation. Expert human assessment also confirms high grammatical accuracy and stylistic fidelity in the generated texts. Beyond expanding the Old English corpus, our method offers a practical blueprint for revitalizing other endangered languages, effectively uniting AI innovation with the goals of cultural preservation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI-Driven Generation of Old English: A Framework for Low-Resource Languages Alva, Rodrigo Gabriel Salazar Nuñez, Matías López, Cristian Arista, Javier Martín Computation and Language Artificial Intelligence Preserving ancient languages is essential for understanding humanity's cultural and linguistic heritage, yet Old English remains critically under-resourced, limiting its accessibility to modern natural language processing (NLP) techniques. We present a scalable framework that uses advanced large language models (LLMs) to generate high-quality Old English texts, addressing this gap. Our approach combines parameter-efficient fine-tuning (Low-Rank Adaptation, LoRA), data augmentation via backtranslation, and a dual-agent pipeline that separates the tasks of content generation (in English) and translation (into Old English). Evaluation with automated metrics (BLEU, METEOR, and CHRF) shows significant improvements over baseline models, with BLEU scores increasing from 26 to over 65 for English-to-Old English translation. Expert human assessment also confirms high grammatical accuracy and stylistic fidelity in the generated texts. Beyond expanding the Old English corpus, our method offers a practical blueprint for revitalizing other endangered languages, effectively uniting AI innovation with the goals of cultural preservation. |
| title | AI-Driven Generation of Old English: A Framework for Low-Resource Languages |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.20111 |