{"url":"/dataset/natural-stories","name":"Natural Stories","full_name":null,"description_markdown":"The Natural Stories dataset consists of English texts edited to contain many low-frequency syntactic constructions while still sounding fluent to native speakers. The corpus is annotated with hand-corrected parse trees and includes self-paced reading time data.\r\n\r\nSource: [The Natural Stories Corpus](/paper/the-natural-stories-corpus)","description_withheld":null,"homepage":"https://github.com/languageMIT/naturalstories","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-natural-stories-corpus","title":"The Natural Stories Corpus","first_author":"Richard Futrell","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Natural Stories"],"data_loaders":[{"repo":"https://github.com/languageMIT/naturalstories","url":"https://github.com/languageMIT/naturalstories","frameworks":[]}],"num_papers_in_archive":24,"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."}