Elamur Research⌕
☰
home / papers / 2015 / Movie Script Summarization as Graph-based Scene Extraction

Movie Script Summarization as Graph-based Scene Extraction

Paper · 2015 · Philip John Gorinski and Mirella Lapata

Summary

Gorinski and Lapata introduce screenplay summarization as a new task. They argue it could help script readers, who must sift through thousands of submissions, by supporting browsing and giving a fast sense of a plot. They treat a summary as an extracted chain of consecutive scenes. A good chain should be important to the story, varied rather than repetitive, and show the story moving from start to finish.

Each script is modelled as a directed bipartite graph of scenes and characters. Edge weights come from linguistic analysis, including how likely a character is to be a main one and how much they interact. Scene-to-scene progression is scored with random walks with restart. The approach adapts an egocentric-video summarization method by Lu and Grauman (2013).

The authors also built ScriptBase, a large corpus of scripts linked to plot summaries and metadata. In a question-answering study on Amazon Mechanical Turk, readers answered more story questions correctly from SceneSum summaries than from baseline summaries. This suggests the model keeps the content that matters most for understanding the narrative.

Key points

  • ScriptBase corpus: 1,276 scripts across 23 genres, spanning 1909–2013.
    • Each film has on average about 3 user summaries, 3 loglines and 3 taglines, aligned via Wikipedia and IMDB.
    • Scripts were processed with Stanford CoreNLP and annotated with semantic roles using MATE tools.
  • Experimental data: experiments used comedies and thrillers, with 30 movies for training/development and 65 for testing.
  • Model (SceneSum): the objective is a weighted sum of three terms (story progression, diversity and importance), optimized under a compression rate.
    • It was compared with MaxOv and MinOv (maximum and minimum character overlap) and a Random baseline.
  • Automatic gold standard: MaxOv achieved the best F1 and SceneSum came second. The authors attribute this to an artifact of how the gold standard was built.
  • Human evaluation: 29 native English speakers answered questions about summaries at 20% compression.
    • SceneSum scored 56.91% correct overall, versus 51.51% (MaxOv), 50.54% (MinOv) and 39.53% (Random).
    • On the plot question, SceneSum reached 73.75%.
    • On the characters question, SceneSum scored lower than MaxOv (37.75% vs 45.54%).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of EdinburghEdinburgh · United Kingdom255 works · 68,771 citations

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 worksComputer Vision and Pattern Recognition · 1,282 works

🧭 Topics 1Research subjects and languages the work is about.Summarization · 159 works

Cite

Cite as Philip John Gorinski and Mirella Lapata. 2015. Movie Script Summarization as Graph-based Scene Extraction. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/n15-1113

@inproceedings{gorinski2015movie,
  title = {{Movie Script Summarization as Graph-based Scene Extraction}},
  author = {Philip John Gorinski and Mirella Lapata},
  booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2015},
  doi = {10.3115/v1/n15-1113},
  url = {https://doi.org/10.3115/v1/n15-1113}
}

References

25 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bamman, David, Brendan O’Connor, and Noah A. Smith. 2013. Learning Latent Personas of Film Characters. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Sofia, Bulgaria, pages 352– 361.
  2. Bamman, David, Ted Underwood, and A. Noah Smith. 2014. A Bayesian Mixed Effects Model of Literary Character. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, MD, USA, pages 370–379.
  3. Björkelund, Anders, Love Hafdell, and Pierre Nugues. 2009. Multilingual Semantic Role Labeling. In Proceedings of the 13th Conference on Computational Natural Language Learning: Shared Task. Boulder, Colorado, pages 43–48.
  4. Clarke, James and Mirella Lapata. 2010. Discourse Constraints for Document Compression. Computational Linguistics 36(3):411–441. find
  5. Elsner, Micha. 2012. Character-based kernels for novelistic plot structure. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Avignon, France, pages 634–644. find
  6. Elson, David K., Nicholas Dames, and Kathleen R. McKeown. 2010. Extracting Social Networks from Literary Fiction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden, pages 138– 147. find
  7. Kim, Jun-Seong, Jae-Young Sim, and Chang-Su Kim. 2014. Multiscale Saliency Detection Using Random Walk With Restart. IEEE Transactions on Circuits and Systems for Video Technology 24(2):198–210. find
  8. Lee, Heeyoung, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task. In Proceedings of the 15th Conference on Computational Natural Language Learning: Shared Task. Portland, OR,…
  9. Lin, C., C. Tsai, L. Kang, and Weisi Lin. 2013. Scene-Based Movie Summarization via Role-Community Networks. IEEE Transactions on Circuits and Systems for Video Technology 23(11):1927–1940. find
  10. Lu, Zheng and Kristen Grauman. 2013. Story-Driven Summarization for Egocentric Video. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA, pages 2714–2721. find
  11. Mani, Inderjeet, Gary Klein, David House, Lynette Hirschman, Therese Firmin, and Beth Sundheim. 2002. SUMMAC: A Text Summarization Evaluation. Natural Language Engineering 8(1):43–68. find
  12. Manning, Christopher, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. pages 55–60.
  13. Michel, Jean-Baptiste, Yuan Kui Shen, aviva Presser Aiden, Adrian Veres, Matthew K. Gray, The Google Books Team, Joseph P. Pickett, Dale Hoiberg, Dan Clancy, Peter Norvig, Jon Orwant, Steven Pinker, Martin A. Nowak, and Erez Liberman Aiden. 2010. Quantitative Analysis of Culture Using Millions of Di… find
  14. Monaco, James. 1982. How to Read a Film: The Art, Technology, Language, History and Theory of Film and Media. OUP, New York, NY, USA. find
  15. Morris, A., G. Kasper, and D. Adams. 1992. The Effects and Limitations of Automated Text Condensing on Reading Comprehension Performance. Information Systems Research 3(1):17– 35. find
  16. Mosteller, Frederick and David Wallace. 1964. Inference and Dispituted Authorship: The Federal-ists. Addison-Wesley, Boston, MA, USA. find
  17. Nalisnick, T. Eric and S. Henry Baird. 2013. Character-to-Character Sentiment Analysis in Shakespeare’s Plays. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Sofia, Bulgaria, pages 479– 483. find
  18. Nelken, Rani and Stuart Shieber. 2006. Towards Robust Context-Sensitive Sentence Alignment for Monolingual Corpora. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics. Trento, Italy, pages 161–168. find
  19. Nielsen, Finn Arup. 2011. A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. In Proceedings of the ESWC2011 Workshop on ’Making Sense of Microposts’: Big Things Come in Small Packages. Heraklion, Crete, pages 93–98. find
  20. Page, Lawrence, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The pagerank citation ranking: Bringing order to the web. Technical Report 1999-66, Stanford InfoLab. Previous number SIDL-WP-1999-0120.
  21. Rasheed, Z., Y. Sheikh, and M. Shah. 2005. On the Use of Computable Features for Film Classification. IEEE Transactions on Circuits and Systems for Video Technology 15(1):52–64. find
  22. Reed, Todd, editor. 2004. Digital Image Sequence Processing. Taylor & Francis. find
  23. Sang, Jitao and Changsheng Xu. 2010. Character-based Movie Summarization. In Proceedings of the International Conference on Multimedia. Firenze, Italy, pages 855–858. find
  24. Tong, Hanghang, Christos Faloutsos, and Jia-Yu Pan. 2006. Fast Random Walk with Restart and Its Applications. In Proceedings of the Sixth International Conference on Data Mining. Hong Kong, pages 613–622. find
  25. Weng, Chung-yi, Wei-Ta Chu, and Ja ling Wu. 2009. Rolenet: Movie Analysis from the perspective of Social Networks. IEEE Transactions on Multimedia 11(2):256–271. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/gorinski-2015-movie-script-summarization-as-graph/