{"url":"/dataset/visualmrc","name":"VisualMRC","full_name":"VisualMRC: Machine Reading Comprehension on Document Images","description_markdown":"VisualMRC is a visual machine reading comprehension dataset that proposes a task: given a question and a document image, a model produces an abstractive answer.\r\n\r\nYou can find more details, analyses, and baseline results in the paper, \r\nVisualMRC: Machine Reading Comprehension on Document Images, AAAI 2021.\r\n\r\n\r\nStatistics:\r\n10,197 images\r\n30,562 QA pairs\r\n10.53 average question tokens (tokenizing with NLTK tokenizer)\r\n9.53 average answer tokens (tokenizing wit NLTK tokenizer)\r\n151.46 average OCR tokens (tokenizing with NLTK tokenizer)","description_withheld":null,"homepage":"https://github.com/nttmdlab-nlp/VisualMRC","introduced_date":"2021-01-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/visualmrc-machine-reading-comprehension-on","title":"VisualMRC: Machine Reading Comprehension on Document Images","first_author":"Ryota Tanaka","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VisualMRC"],"data_loaders":[{"repo":"https://github.com/nttmdlab-nlp/VisualMRC","url":"https://github.com/nttmdlab-nlp/VisualMRC","frameworks":[]}],"num_papers_in_archive":36,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-visualmrc","task":"Visual Question Answering","dataset_variant":"VisualMRC","rows":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"LayoutT5 (Large)","paper":"/paper/visualmrc-machine-reading-comprehension-on","metrics":{"CIDEr":"364.2"},"code_links":[{"title":"nttmdlab-nlp/VisualMRC","url":"https://github.com/nttmdlab-nlp/VisualMRC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/visualmrc-machine-reading-comprehension-on","title":"VisualMRC: Machine Reading Comprehension on Document Images","date":"2021-01-27","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}