AI-Driven Generation of Old English: A Framework for Low-Resource Languages

2025-07-26

AI Summary

The scarcity of Old English corpora severely limits its applicability in modern NLP. To address this, we propose a dual-agent generative framework that decouples content generation from stylistic transfer: one agent employs LoRA-efficient fine-tuning of large language models to generate authentic Old English exemplars; the other enhances linguistic fidelity via back-translation. Our approach integrates parameter-efficient fine-tuning, back-translation-based data augmentation, and automated evaluation (BLEU, METEOR, chrF), validated by linguistics experts. Experiments demonstrate a substantial improvement in Old English translation quality—BLEU scores rise significantly from 26 to over 65—while achieving high grammatical accuracy and stylistic consistency. The method effectively expands high-quality, reproducible Old English resources, establishing a novel paradigm for computational research on historical languages.

Technology Category

• Natural Language Processing: Generation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• Addressing under-resourced Old English for NLP accessibility
• Generating high-quality Old English texts using LLMs
• Providing a scalable framework for endangered language revitalization

Innovation

• Uses LLMs for Old English text generation
• Combines LoRA and backtranslation techniques
• Employs dual-agent pipeline for translation