{"url":"/dataset/csi-screenplay-summarization-corpus","name":"CSI Screenplay Summarization Corpus","full_name":null,"description_markdown":"The dataset contains gold-standard summary labels for 39 \"CSI: Crime Scene Investigation\" episodes from seasons 1-5. Each episode contains the full-length screenplay and human annotations for its summary. The annotations include:\r\n\r\n1. scene-level binary labels denoting whether the scene belongs to the summary of the episode\r\n2. aspect-based labels for the scenes that belong to the summary, i.e., which aspect of the summary the scene addresses (e.g., information about the victim, the crime scene, the perpetrator etc.)\r\n3. sentence-level binary labels denoting the sentences of the screenplay that belong to the summary for 10 episodes of the dataset","description_withheld":null,"homepage":"https://github.com/EdinburghNLP/csi-corpus","introduced_date":"2020-04-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/screenplay-summarization-using-latent","title":"Screenplay Summarization Using Latent Narrative Structure","first_author":"Pinelopi Papalampidi","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CSI Screenplay Summarization Corpus"],"data_loaders":[{"repo":"https://github.com/EdinburghNLP/csi-corpus","url":"https://github.com/EdinburghNLP/csi-corpus","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."}