{"url":"/dataset/shmoop-corpus","name":"Shmoop Corpus","full_name":null,"description_markdown":"Shmoop Corpus is a dataset of 231 stories that are paired with detailed multi-paragraph summaries for each individual chapter (7,234 chapters), where the summary is chronologically aligned with respect to the story chapter. From the corpus, a set of common NLP tasks are constructed, including Cloze-form question answering and a simplified form of abstractive summarization, as benchmarks for reading comprehension on stories.\r\n\r\nSource: [Shmoop Corpus](http://www.cs.toronto.edu/~makarand/shmoop/)","description_withheld":null,"homepage":"http://www.cs.toronto.edu/~makarand/shmoop/","introduced_date":"2019-12-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-shmoop-corpus-a-dataset-of-stories-with","title":"The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries","first_author":"Atef Chaudhury","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"}],"languages":[],"variants":["Shmoop Corpus"],"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."}