{"url":"/dataset/ilur-news-texts","name":"iLur News Texts","full_name":null,"description_markdown":"iLur News Texts is a dataset of over 12000 news articles from iLur.am, categorized into 7 classes: sport, politics, weather, economy, accidents, art, society. The articles are split into train (2242k tokens) and test sets (425k tokens).\r\n\r\nSource: [iLur News Texts](https://github.com/ispras-texterra/word-embeddings-eval-hy)","description_withheld":null,"homepage":"https://github.com/ispras-texterra/word-embeddings-eval-hy","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/word-embeddings-for-the-armenian-language","title":"Word Embeddings for the Armenian Language: Intrinsic and Extrinsic Evaluation","first_author":"Karen Avetisyan","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"},{"name":"Morphological Tagging","url":"/task/morphological-tagging","datasets_with_task":"/datasets/task/morphological-tagging"}],"languages":[],"variants":["iLur News Texts"],"data_loaders":[{"repo":"https://github.com/ispras-texterra/word-embeddings-eval-hy","url":"https://github.com/ispras-texterra/word-embeddings-eval-hy","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."}