{"url":"/dataset/summscreen","name":"SummScreen","full_name":null,"description_markdown":"SummScreen is a dataset for abstractive screenplay summarization. It consists of pairs of TV series transcripts and human-written recaps. This dataset provides a challenging testbed for abstractive summarization for several reasons:\r\n- Plot details are often expressed indirectly in character dialogues and may be scattered across the entirety of the transcript.\r\n- These details must be found and integrated to form the succinct plot descriptions in the recaps.\r\n- TV scripts contain content that does not directly pertain to the central plot but rather serves to develop characters or provide comic relief. This information is rarely contained in recaps.","description_withheld":null,"homepage":"https://github.com/mingdachen/SummScreen","introduced_date":"2021-04-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/summscreen-a-dataset-for-abstractive","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","first_author":"Mingda Chen","url":null},"license":null,"modalities":[],"tasks":[{"name":"Long-Form Narrative Summarization","url":"/task/long-form-narrative-summarization","datasets_with_task":"/datasets/task/long-form-narrative-summarization"}],"languages":[],"variants":["SummScreen"],"data_loaders":[],"num_papers_in_archive":60,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/long-form-narrative-summarization-on","task":"Long-Form Narrative Summarization","dataset_variant":"SummScreen","rows":5,"metrics":["BERTScore (F1)","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"NexusSum (Mistral Large)","paper":"/paper/nexussum-hierarchical-llm-agents-for-long","metrics":{"BERTScore (F1)":"61.59","ROUGE-1":"30.44","ROUGE-2":"6.40","ROUGE-L":"17.95"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/nexussum-hierarchical-llm-agents-for-long","title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","date":"2025-05-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-long-document-summarization-using","title":"End-to-End Long Document Summarization using Gradient Caching","date":"2025-01-03","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"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."}