{"url":"/dataset/lepiszcze","name":"LEPISZCZE","full_name":null,"description_markdown":"**LEPISZCZE** is an open-source comprehensive benchmark for Polish NLP and a continuous-submission leaderboard, concentrating public Polish datasets (existing and new) in specific tasks.\r\n\r\nSource: [This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish](https://arxiv.org/pdf/2211.13112v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.13112v1.pdf](https://arxiv.org/pdf/2211.13112v1.pdf)","description_withheld":null,"homepage":"https://github.com/CLARIN-PL/LEPISZCZE","introduced_date":"2022-11-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/this-is-the-way-designing-and-compiling","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","first_author":"Łukasz Augustyniak","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"},{"name":"Punctuation Restoration","url":"/task/punctuation-restoration","datasets_with_task":"/datasets/task/punctuation-restoration"}],"languages":[{"name":"Polish","url":"/datasets/language/polish"}],"variants":["LEPISZCZE"],"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."}