{"url":"/dataset/gutenberg-dialog-dataset","name":"Gutenberg Dialog Dataset","full_name":null,"description_markdown":"This is a high-quality dataset consisting of 14.8M utterances in English, extracted from processed dialogues from publicly available online books.\n\nSource: [https://github.com/ricsinaruto/gutenberg-dialog](https://github.com/ricsinaruto/gutenberg-dialog)","description_withheld":null,"homepage":"https://github.com/ricsinaruto/gutenberg-dialog","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-gutenberg-dialogue-dataset","title":"The Gutenberg Dialogue Dataset","first_author":"Richard Csaky","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Dialog","url":"/datasets/modality/dialog"}],"tasks":[],"languages":[],"variants":["Gutenberg Dialog Dataset"],"data_loaders":[{"repo":"https://github.com/ricsinaruto/gutenberg-dialog","url":"https://github.com/ricsinaruto/gutenberg-dialog","frameworks":[]}],"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."}