{"url":"/dataset/rubq","name":"RuBQ","full_name":"Russian Knowledge Base Questions","description_markdown":"The first Russian knowledge base question answering (KBQA) dataset. The high-quality dataset consists of 1,500 Russian questions of varying complexity, their English machine translations, SPARQL queries to Wikidata, reference answers, as well as a Wikidata sample of triples containing entities with Russian labels. The dataset creation started with a large collection of question-answer pairs from online quizzes. The data underwent automatic filtering, crowd-assisted entity linking, automatic generation of SPARQL queries, and their subsequent in-house verification.\r\n\r\nSource: [RuBQ: A Russian Dataset for Question Answering over Wikidata](/paper/rubq-a-russian-dataset-for-question-answering)","description_withheld":null,"homepage":"https://github.com/vladislavneon/RuBQ","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/rubq-a-russian-dataset-for-question-answering","title":"RuBQ: A Russian Dataset for Question Answering over Wikidata","first_author":"Vladislav Korablinov","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["RuBQ"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/d0rj/RuBQ_2.0-paragraphs","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/d0rj/RuBQ_1.0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/d0rj/RuBQ_2.0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/vladislavneon/RuBQ","url":"https://github.com/vladislavneon/RuBQ","frameworks":[]}],"num_papers_in_archive":7,"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."}