{"url":"/dataset/korpus-malti","name":"Korpus Malti","full_name":null,"description_markdown":"General Corpora for the Maltese Language.","description_withheld":null,"homepage":"https://huggingface.co/datasets/MLRS/korpus_malti","introduced_date":"2022-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","first_author":"Kurt Micallef","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License","url":"http://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Maltese","url":"/datasets/language/maltese"}],"variants":["Korpus Malti"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}