{"url":"/dataset/vlogqa","name":"VlogQA","full_name":"Vietnamese Spoken-Based Machine Reading Comprehension","description_markdown":"The VlogQA consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube - an extensive source of user-uploaded content, covering the topics of food and travel in the Vietnamese language. This dataset is used for research in Vietnamese Spoken-Based Machine Reading Comprehension.","description_withheld":null,"homepage":"https://github.com/sonlam1102/vlogqa","introduced_date":"2024-02-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/vlogqa-task-dataset-and-baseline-models-for","title":"VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension","first_author":"Thinh Phuoc Ngo","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Spoken Language Understanding","url":"/task/spoken-language-understanding","datasets_with_task":"/datasets/task/spoken-language-understanding"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["VlogQA"],"data_loaders":[],"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."}