Screenplay Summarization Using Latent Narrative Structure

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.

When a Robot Writes a Play: Automatically Generating a Theatre Play Script

“…The text is generated word by word and line by line, whereas human authors of theatre plays typically operate on a more abstract level, such as dramatic situations (Polti, 1921). 6 While there is some work on identifying dramatic turning points (Papalampidi et al, 2019(Papalampidi et al, , 2020, it is too coarse-grained for our application. We are thus currently annotating a corpus of theatre play scripts with a modified set of dramatic situations, and plan to enhance the tool with this abstraction, either by adding one more layer in the hierarchical setup, or by using special tokens or embeddings to mark dramatic situations in the generated text.…”

Proceedings of the Third Workshop on Narrative Understanding

“…The goal of screenplay summarization is to help speeding up script browsing; to provide an overview of the script's contents and storyline; and to reduce the reading time (Gorinski and Lapata, 2015). As shown in Figure 2, to make this long narrative-text summarization feasible, early work in screenplay summarization (Gorinski and Lapata, 2015;Papalampidi et al, 2020a) defined the task as extracting a sequence of scenes that represents informative summary (i.e., scene-level extractive summarization).…”

“…Text summarization is one major task in NLP that seeks to produce concise texts containing only the essential information in the original texts. Although most researches have been focusing on summarizing news articles (Narayan et al, 2018;See et al, 2017), as various contents with different structures increase these days, there has been growing interests in applying text summarization to various domains, including social media (Sharifi et al, 2010;Kim and Monroy-Hernandez, 2016), dialogue (Goo and Chen, 2018), scientific articles (Cohan and Goharian, 2017; Yasunaga et al, 2019), books (Mihalcea and Ceylan, 2007), screenplays (or scripts) (Gorinski and Lapata, 2015;Papalampidi et al, 2020a). Among them, this paper focuses on screenplay summarization.…”

Film Trailer Generation via Task Decomposition

“…Previous approaches to movie understanding have mainly focused on isolated video clips, and tasks such as the alignment between movie scenes and book chapters [49], question answering [50], video captioning for movie shots [44], and text-to-video retrieval [5]. Recent work [40][41][42] attempts to identify high-level narrative structure and summarize entire TV episodes and movies focusing exclusively on the textual modality (i.e., screenplays).…”