{"url":"/dataset/lenta-short-sentences","name":"Lenta Short Sentences","full_name":null,"description_markdown":"The **Lenta Short Sentences** dataset is a text dataset for language modelling for the Russian language. It consists of 236K sentences sampled from the Lenta News dataset.\n\nSource: [https://arxiv.org/pdf/2005.02470.pdf](https://arxiv.org/pdf/2005.02470.pdf)","description_withheld":null,"homepage":"https://github.com/zeinsh/lenta_short_sentences","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/russian-natural-language-generation-creation","title":"Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures","first_author":"Zein Shaheen","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["Lenta Short Sentences"],"data_loaders":[{"repo":"https://github.com/zeinsh/lenta_short_sentences","url":"https://github.com/zeinsh/lenta_short_sentences","frameworks":[]}],"num_papers_in_archive":1,"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."}