AQUILIGN is a multilingual alignment and collation tool for 📜 medieval texts. It uses ✂️ clause-level segmentation and 🔗 contextual alignment based on BERT models, with applications in 🌍 historical linguistics, 📖 philology, and 🤖 premodern NLP.

Segmentation data used in multilingual alignment tasks across English, French, Spanish, and other languages. Includes raw and segmented text files for training and evaluation.