# Screenplay Summarization Using Latent Narrative Structure

arXiv: https://arxiv.org/abs/2004.12727 · HTML: https://mlsanity.com/paper/2004.12727/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [MeetingBank: A Benchmark Dataset for Meeting Summarization](https://mlsanity.com/paper/2305.17529/) (2023)
- [SummScreen: A Dataset for Abstractive Screenplay Summarization](https://mlsanity.com/paper/2104.07091/) (2021)
- [SNaC: Coherence Error Detection for Narrative Summarization](https://mlsanity.com/paper/2205.09641/) (2022)
- [StreamHover: Livestream Transcript Summarization and Annotation](https://mlsanity.com/paper/2109.05160/) (2021)
- [Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition](https://mlsanity.com/paper/2111.08774/) (2021)
- [A Survey of Machine Narrative Reading Comprehension Assessments](https://mlsanity.com/paper/2205.00299/) (2022)
- [Select and Summarize: Scene Saliency for Movie Script Summarization](https://mlsanity.com/paper/2404.03561/) (2024)
- [Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding](https://mlsanity.com/paper/2203.05711/) (2022)
- [MovieSum: An Abstractive Summarization Dataset for Movie Screenplays](https://mlsanity.com/paper/2408.06281/) (2024)
- [Long Story Short: a Summarize-then-Search Method for Long Video Question Answering](https://mlsanity.com/paper/2311.01233/) (2023)
- [NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization](https://mlsanity.com/paper/2212.01476/) (2022)
- [Movie Facts and Fibs (MF2): A Benchmark for Long Movie Understanding](https://mlsanity.com/paper/2506.06275/) (2025)
- [MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation](https://mlsanity.com/paper/2308.11185/) (2023)
- [VisAgent: Narrative-Preserving Story Visualization Framework](https://mlsanity.com/paper/2503.02399/) (2025)
- [THEaiTRE 1.0: Interactive generation of theatre play scripts](https://mlsanity.com/paper/2102.08892/) (2021)
- [M-SENSE: Modeling Narrative Structure in Short Personal Narratives Using Protagonist's Mental Representations](https://mlsanity.com/paper/2302.09418/) (2023)
- [Prosody Analysis of Audiobooks](https://mlsanity.com/paper/2310.06930/) (2023)
- [Previously on the Stories: Recap Snippet Identification for Story Reading](https://mlsanity.com/paper/2402.07271/) (2024)
- [DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph](https://mlsanity.com/paper/2410.14666/) (2024)
- [Analysing the Memorability of a Procedural Crime-Drama TV Series, CSI](https://mlsanity.com/paper/2208.03479/) (2022)
- ["Previously on ..." From Recaps to Story Summarization](https://mlsanity.com/paper/2405.11487/) (2024)
- [SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence](https://mlsanity.com/paper/2605.31529/) (2026)
- [An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays](https://mlsanity.com/paper/2610.15544/) (2026)

## Abstract (arXiv)

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 on 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.