{"url":"/dataset/vimq","name":"ViMQ","full_name":null,"description_markdown":"**ViMQ** is a Vietnamese dataset of medical questions from patients with sentence-level and entity-level annotations for the Intent Classification and Named Entity Recognition tasks. It contains Vietnamese medical questions crawled from the consultation section online between patients and doctors from www.vinmec.com, a website of a Vietnamese general hospital. Each consultation consists of a question regarding a specific health issue of a patient and a detailed respond provided by a clinical expert. The dataset contains health issues that fall into a wide range of categories including common illness, cardiology, hematology, cancer, pediatrics, etc. We removed sections where users ask about information of the hospital and selected 9,000 questions for the dataset.\r\n\r\nSource: [ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development](https://arxiv.org/pdf/2304.14405v1.pdf)","description_withheld":null,"homepage":"https://github.com/tadeephuy/vimq","introduced_date":"2023-04-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/vimq-a-vietnamese-medical-question-dataset","title":"ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development","first_author":"Ta Duc Huy","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["ViMQ"],"data_loaders":[],"num_papers_in_archive":3,"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."}