Movie Script Summarization as Graph-based Scene Extraction

By Philip John Gorinski, Mirella Lapata. 2015

86 citations recorded by the source corpus.

In this paper we study the task of movie script summarization, which we argue could enhance script browsing, give readers a rough idea of the script’s plotline, and speed up reading time. We formalize the process of generating a shorter version of a screenplay as the task of finding an optimal chain of scenes. We develop a graph-based model that selects a chain by jointly optimizing its logical progression, diversity, and importance. Human evaluation based on a question-answering task shows that our model produces summaries which are more informative compared to competitive baselines.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

The NarrativeQA Reading Comprehension Challenge (2017, background): “modeling objectives has become an important subproblem in NLP. These include high level plot understanding through clustering of novels (Frermann and Szarvas, 2017) or summarization of movie scripts (Gorinski and Lapata, 2015), to more ﬁne grained processing by inducing character types (Bamman et al”
Recursively Summarizing Books with Human Feedback (2021, methodology): “Early work (Gorinski and Lapata, 2015) used graph-based methods to summarize movie scripts.”
Connotation Frames of Power and Agency in Modern Films (2017, methodology): “We use 772 movie scripts from (Gorinski and Lapata, 2015) as a test bed to validate our new connotation frames.”
PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, methodology): “We draw our data from the 767 modern English movie scripts by Gorinski and Lapata (2015), focusing on the narrations which describe characters and their actions (as opposed to the character’s dialogue utterances).”
Recent advances in document summarization (2017, background): “scripts [64], entity descriptions in knowledge graphs [27], and source codes descriptions [80].”
Intrinsic Evaluation of Summarization Datasets (2020, methodology): “MovieScript (Gorinski and Lapata, 2015) is a dataset of movie scripts drawn from the Script-”
Efficient Attentions for Long Document Summarization (2021, background): “Summarizing long inputs has been investigated in many domains, including books (Mihalcea and Ceylan, 2007), patents (Trappey et al., 2009), movie scripts (Gorinski and Lapata, 2015), and sci-entiﬁc publications (Qazvinian and Radev, 2008).”
SummScreen: A Dataset for Abstractive Screenplay Summarization (2021, background): “play summarization (Gorinski and Lapata, 2015; Papalampidi et al., 2020), and analyzing crime drama (Frermann et al.”
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018, methodology): “For our portrayal analyses, we use scene descriptions from 772 movie scripts released by Gorinski and Lapata (2015), assigned to over 21,000 characters as done by Sap et al.”
Zero-Shot Activity Recognition with Verb Attribute Induction (2017, methodology): “We selected all verbs from the ImSitu corpus, consisting of images representing verbs from many categories (Yatskar et al., 2016), then extended the set using the MPII movie visual description dataset and ScriptBase datasets, (Rohrbach et al., 2015; Gorinski and Lapata, 2015).”
LLM as a Broken Telephone: Iterative Generation Distorts Information (2025, unknown): “We utilized three datasets that span distinct domains: BookSum (Kry´sci´nski et al., 2021), ScriptBase-alpha (Gorinski and Lapata, 2015), and (BBC)News2024 (Li et al., 2024a), from which we select articles published in 2024 to minimize the chances of data exposure that may result in biases…”