{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/select-and-summarize-scene-saliency-for-movie","title":"Select and Summarize: Scene Saliency for Movie Script Summarization","arxiv_id":"2404.03561","date":"2024-04-04","proceeding":null,"authors":["Rohit Saxena","Frank Keller"],"abstract":"Abstractive summarization for long-form narrative texts such as movie scripts is challenging due to the computational and memory constraints of current language models. A movie script typically comprises a large number of scenes; however, only a fraction of these scenes are salient, i.e., important for understanding the overall narrative. The salience of a scene can be operationalized by considering it as salient if it is mentioned in the summary. Automatically identifying salient scenes is difficult due to the lack of suitable datasets. In this work, we introduce a scene saliency dataset that consists of human-annotated salient scenes for 100 movies. We propose a two-stage abstractive summarization approach which first identifies the salient scenes in script and then generates a summary using only those scenes. Using QA-based evaluation, we show that our model outperforms previous state-of-the-art summarization methods and reflects the information content of a movie more accurately than a model that takes the whole movie script as input.","url_abs":"https://arxiv.org/abs/2404.03561v1","url_pdf":"https://arxiv.org/pdf/2404.03561v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"select-and-summarize-scene-saliency-for-movie","repo_url":"https://github.com/saxenarohit/select_summ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"long-form-narrative-summarization","task_name":"Long-Form Narrative Summarization"}],"methods":[],"datasets_introduced":[{"slug":"mensa","name":"MENSA","full_name":"Movie Scene Saliency Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","task":"Long-Form Narrative Summarization","dataset":"MENSA","model":"SELECT & SUMM (LED)","rank_in_archive_order":6,"of":10,"metrics":{"BERTScore (F1)":"57.46"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","task":"Long-Form Narrative Summarization","dataset":"MENSA","model":"Two-Stage Heuristic (LED Large)","rank_in_archive_order":7,"of":10,"metrics":{"BERTScore (F1)":"56.34"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","task":"Long-Form Narrative Summarization","dataset":"MENSA","model":"SUMM-N Multi Stage","rank_in_archive_order":10,"of":10,"metrics":{"BERTScore (F1)":"40.87"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03561","atlas_url":"https://app.syntology.ai/?focus=2404.03561","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}