Screenplay Summarization Using Latent Narrative Structure
Pinelopi Papalampidi, Frank Keller, Lea Frermann, Mirella Lapata
Abstract
Most general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront. As a result, such models are biased by position and often perform a smart selection of sentences from the beginning of the document. When summarizing long narratives, which have complex structure and present information piecemeal, simple position heuristics are not sufficient. In this paper, we propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays (i.e., extract an optimal sequence of scenes). Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode and improve summarization performance over general extractive algorithms, leading to more complete and diverse summaries. Victim: Mike Kimble, found in a Body Farm. Died 6 hours ago, unknown cause of death. CSI discover cow tissue in Mike's body. Cross-contamination is suggested. Probable cause of death: Mike's house has been set on fire. CSI finds blood: Mike was murdered, fire was a cover up. First suspects: Mike's fiance, Jane and her ex-husband, Russ. CSI finds photos in Mike's house of Jane's daughter, Jodie, posing naked. Mike is now a suspect of abusing Jodie. Russ allows CSI to examine his gun. CSI discovers that the bullet that killed Mike was made of frozen beef that melt inside him. They also find beef in Russ' gun. Russ confesses that he knew that Mike was abusing Jody, so he confronted and killed him. CSI discovers that the naked photos were taken on a boat, which belongs to Russ. CSI discovers that it was Russ who was abusing his daughter based on fluids found in his sleeping bag and later killed Mike who tried to help Jodie. Russ is given bail, since no jury would convict a protective father.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 4dc3c5fb-f71f-4e6f-9acb-0b17ad7393f0Cited by top-tier papers8
- Movie Summarization via Sparse Graph ConstructionPinelopi Papalampidi, Frank Keller, Mirella LapataAAAI 2021 · 36 citations
- MeetingBank: A Benchmark Dataset for Meeting SummarizationYebowen Hu, Timothy Ganter, Hanieh Deilamsalehy, Franck Dernoncourt et al.ACL 2023 · 19 citations
- SNaC: Coherence Error Detection for Narrative SummarizationTanya Goyal, Junyi Jessy Li, Greg DurrettEMNLP 2022 · 19 citations
- StreamHover: Livestream Transcript Summarization and AnnotationSangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui et al.EMNLP 2021 · 18 citations
- MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video SegmentationNajmeh Sadoughi, Xinyu Li, Avijit Vajpayee, David Fan et al.ICCV 2023 · 6 citations
Related papers
- Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News EventsPriyanka Kargupta, Yunyi Zhang, Yizhu Jiao, Siru Ouyang et al.ACL 2025
- NexusSum: Hierarchical LLM Agents for Long-Form Narrative SummarizationHyuntak Kim, Byung-Hak KimACL 2025
- Integrating Deep Event-Level and Script-Level Information for Script Event PredictionLong Bai, Saiping Guan, Jiafeng Guo, Zixuan Li et al.EMNLP 2021 · 25 citations
- Are Large Language Models Capable of Generating Human-Level Narratives?Yufei Tian, Tenghao Huang, Miri Liu, Derek Jiang et al.EMNLP 2024 · 22 citations
- Make LLMs See Like Investigators, Not Just Think More: The Role of Structured Analysis in Investigative ReasoningJaewook Lee, Myeong-Cheol Kang, Jong-hun ShinACL 2026
