{"url":"/dataset/uit-vinewsqa","name":"UIT-ViNewsQA","full_name":null,"description_markdown":"UIT-ViNewsQA is a new corpus for the Vietnamese language to evaluate healthcare reading comprehension models. The corpus comprises 22,057 human-generated question-answer pairs. Crowd-workers create the questions and their answers based on a collection of over 4,416 online Vietnamese healthcare news articles, where the answers comprise spans extracted from the corresponding articles. \r\n\r\nSource: [New Vietnamese Corpus for Machine ReadingComprehension of Health News Articles](/paper/new-vietnamese-corpus-for-machine)","description_withheld":null,"homepage":"https://sites.google.com/uit.edu.vn/kietnv/datasets","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/new-vietnamese-corpus-for-machine","title":"New Vietnamese Corpus for Machine Reading Comprehension of Health News Articles","first_author":"Kiet Van Nguyen","url":null},"license":null,"modalities":[],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["UIT-ViNewsQA"],"data_loaders":[],"num_papers_in_archive":5,"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."}