{"url":"/dataset/chart2text","name":"Chart2Text","full_name":"Chart Summarization Dataset","description_markdown":"Chart2Text is a dataset that was crawled from 23,382 freely accessible pages from statista.com in early March of 2020, yielding a total of 8,305 charts, and associated summaries. For each chart, the chart image, the underlying data table, the title, the axis labels, and a human-written summary describing the statistic was downloaded.\r\n\r\nSource: [Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model](https://arxiv.org/pdf/2010.09142.pdf)","description_withheld":null,"homepage":"https://github.com/JasonObeid/Chart2Text","introduced_date":"2020-10-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/chart-to-text-generating-natural-language","title":"Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model","first_author":"Jason Obeid","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"}],"languages":[],"variants":["Chart2Text"],"data_loaders":[{"repo":"https://github.com/JasonObeid/Chart2Text","url":"https://github.com/JasonObeid/Chart2Text","frameworks":[]}],"num_papers_in_archive":10,"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."}