@inproceedings{kabashi-ruppert-2026-merimenga, title = {Merim{\"e}nga: A Manifest-First Pipeline for Reproducible {A}lbanian Web Corpus Construction}, author = "Kabashi, Besim and Ruppert, Michael", editor = "Ba{\'n}ski, Piotr and Knight, Dawn and Kupietz, Marc and Witt, Andreas and Wr{\'o}blewska, Alina", booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora", month = may, year = "2026", address = "Palma, Mallorca (Spain)", publisher = "ELRA Language Resources Association (ELRA)", url = "https://aclanthology.org/2026.cmlc-1.3/", doi = "10.63317/4aesmyqqveeo", pages = "25--31" }