Elamur Research⌕
☰
home / papers / 2023 / Character Coreference Resolution in Movie Screenplays

Character Coreference Resolution in Movie Screenplays

Summary

Screenplays are long and semi-structured. A typical script runs about 30K words, which is far beyond the 512-token window of standard transformer encoders, and characters often return to the story many scenes after their last mention. Baruah and Narayanan address two linked problems: recovering a script's structure and grouping all mentions of each character. For parsing, they take 39 annotated screenplay excerpts and add synthetic formatting noise, such as stripped indentation, watermarks and sluglines without INT/EXT. A sequence-embedding parser trained on this data labels each line as slugline, action, speaker, expression, utterance or transition. For coreference, they annotate six full-length screenplays and extend Dobrovolskii's (2021) word-level model with a character scorer module. They also propose two inference schemes for long documents: fusing scores from overlapping subdocuments, and a hierarchical second pass over cluster representatives. The parser holds up better on noisy scripts than a rule-based baseline. Both coreference methods beat the earlier screenplay baseline while keeping GPU memory modest, which makes full-script character analysis practical.

Key points

  • Released resources: MovieParse (screenplay parsing data) and MovieCoref (character coreference over six full-length scripts), with code on GitHub under usc-sail.
  • Memory limit motivating the work: quadratic mention-pair scoring is the bottleneck, and a 48 GB GPU could only handle documents of about 20K tokens.
  • Character scorer ablation: adding the module raises fusion-based LEA F1 from 72.2 to 74.2, and a similar gain appears for hierarchical inference.
  • Fusion vs. hierarchical inference:
    • Main settings: fusion uses 5120-word subdocuments with 2048-word overlap; hierarchical uses non-overlapping 5120-word chunks with 3 representative words per cluster.
    • Accuracy: the two do not differ significantly in F1.
    • Trade-off: hierarchical inference gains about 10 points of LEA recall but loses about 11 points of precision.
    • Scaling: larger subdocuments and overlaps improve scores.
  • Limitations:
    • No plural mentions or singleton clusters.
    • Only linear-narrative films.
    • At least 10 GB of GPU memory is needed.

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

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

7 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 5 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.findings-acl.654

@inproceedings{baruah2023character,
  title = {{Character Coreference Resolution in Movie Screenplays}},
  author = {Baruah, Sabyasachee and Narayanan, Shrikanth},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2023},
  year = {2023},
  doi = {10.18653/v1/2023.findings-acl.654},
  url = {https://doi.org/10.18653/v1/2023.findings-acl.654}
}

References

45 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Apoorv Agarwal, Sriramkumar Balasubramanian, Jiehan Zheng, and Sarthak Dash. 2014. Parsing screenplays for extracting social networks from movies. In Proceedings of the 3rd Workshop on Computational Linguistics for Literature (CLFL), pages 50–58, Gothenburg, Sweden. Association for Computational Lin… find
  2. Paul Argentini. 1998. Elements of Style for Screen Writers. Lone Eagle Publishing Company. find
  3. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563–566. Citeseer. find our card
  4. David Bamman, Olivia Lewke, and Anya Mansoor. 2020. An annotated dataset of coreference in English literature. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 44–54, Marseille, France. European Language Resources Association. find our card
  5. David Bamman, 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 (Volume 1: Long Papers), pages 352–361, Sofia, Bulgaria. Association for Computational Linguistics. find our card
  6. David Bamman, Sejal Popat, and Sheng Shen. 2019. An annotated dataset of literary entities. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2138–2144, Minneapoli… find
  7. Sabyasachee Baruah, Sandeep Nallan Chakravarthula, and Shrikanth Narayanan. 2021. Annotation and evaluation of coreference resolution in screenplays. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2004–2010, Online. Association for Computational Linguistics. find
  8. Bernd Bohnet, Chris Alberti, and Michael Collins. 2022. Coreference resolution through a seq2seq transition-based system. find our card
  9. Mariona Coll Ardanuy and Caroline Sporleder. 2014. Structure-based clustering of novels. In Proceedings of the 3rd Workshop on Computational Linguistics for Literature (CLFL), pages 31–39, Gothenburg, Sweden. Association for Computational Linguistics. find
  10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  11. Vladimir Dobrovolskii. 2021. Word-level coreference resolution. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7670–7675, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find our card
  12. Micha Elsner. 2012. Character-based kernels for novel-istic plot structure. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 634–644, Avignon, France. Association for Computational Linguistics. find
  13. David Elson, Nicholas Dames, and Kathleen McKeown. 2010. Extracting social networks from literary fiction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 138–147, Uppsala, Sweden. Association for Computational Linguistics. find
  14. Philip John Gorinski and Mirella Lapata. 2015. Movie script summarization as graph-based scene extraction. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1066–1076, Denver, Colorado. Association… find
  15. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spacy: Industrial-strength natural language processing in python. find
  16. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. Span-BERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. find our card
  17. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP… find our card
  18. Yuval Kirstain, Ori Ram, and Omer Levy. 2021. Coreference resolution without span representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 14–… find our card
  19. Vincent Labatut and Xavier Bost. 2019. Extraction and analysis of fictional character networks. ACM Computing Surveys, 52(5):1–40. find
  20. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  21. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 687–… find our card
  22. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25–32. find our card
  23. Victor R. Martinez, Krishna Somandepalli, and Shrikanth Narayanan. 2022. Boys don’t cry (or kiss or dance): A computational linguistic lens into gendered actions in film. PLOS ONE, 17(12):1–23. find
  24. Nafise Sadat Moosavi and Michael Strube. 2016. Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 632–642, Berlin, Germany. Associ… find our card
  25. Eric T. Nalisnick and Henry S. Baird. 2013. Character-to-character sentiment analysis in shakespeare’s plays. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 479–483, Sofia, Bulgaria. Association for Computational Linguistics… find
  26. Andrew Piper, Richard Jean So, and David Bamman. 2021. Narrative theory for computational narrative understanding. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 298–311, Online and Punta Cana, Dominican Republic. Association for Computational Lingui… find
  27. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguisti… find our card
  28. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2022. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(1). find
  29. Anil Ramakrishna, Victor R. Martínez, Nikolaos Ma-landrakis, Karan Singla, and Shrikanth Narayanan. 2017. Linguistic analysis of differences in portrayal of movie characters. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 166… find
  30. Nils Reiter. 2018. CorefAnnotator - A New Annotation Tool for Entity References. In Abstracts of EADH: Data in the Digital Humanities. find
  31. Christopher Riley. 2009. The Hollywood standard: the complete and authoritative guide to script format and style. Michael Wiese Productions. find
  32. Maarten Sap, Marcella Cindy Prasettio, Ari Holtzman, Hannah Rashkin, and Yejin Choi. 2017. Connotation frames of power and agency in modern films. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2329–2334, Copenhagen, Denmark. Association for Computat… find
  33. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Advances in Neural Information Processing Systems, 33:16857– 16867. find our card
  34. Shashank Srivastava, Snigdha Chaturvedi, and Tom Mitchell. 2016. Inferring interpersonal relations in narrative summaries. find
  35. Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan, and Andrew McCallum. 2021. Scaling within document coreference to long texts. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3921–3931, Online. Association for Computation… find our card
  36. Shubham Toshniwal, Sam Wiseman, Allyson Ettinger, Karen Livescu, and Kevin Gimpel. 2020. Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8519–8526, Online. Asso… find our card
  37. R. Turetsky and N. Dimitrova. 2004. Screenplay alignment for closed-system speaker identification and analysis of feature films. In 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763), volume 3, pages 1659–1662 Vol.3. find
  38. Hardik Vala, David Jurgens, Andrew Piper, and Derek Ruths. 2015. Mr. bennet, his coachman, and the archbishop walk into a bar but only one of them gets recognized: On the difficulty of detecting characters in literary texts. In Proceedings of the 2015 Conference on Empirical Methods in Natural Langu… find
  39. Dieter Van Rijsselbergen, Barbara Van De Keer, Maarten Verwaest, Erik Mannens, and Rik Van de Walle. 2009. Movie script markup language. In Proceedings of the 9th ACM Symposium on Document Engineering, DocEng ’09, page 161–170, New York, NY, USA. Association for Computing Machinery. find
  40. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995. find our card
  41. David R Winer and R Michael Young. 2017. Automated screenplay annotation for extracting storytelling knowledge. In Thirteenth Artificial Intelligence and Interactive Digital Entertainment Conference. find
  42. Patrick Xia, João Sedoc, and Benjamin Van Durme. 2020. Incremental neural coreference resolution in constant memory. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8617–8624, Online. Association for Computational Linguistics. find our card
  43. Michael Yoder, Sopan Khosla, Qinlan Shen, Aakanksha Naik, Huiming Jin, Hariharan Muralidharan, and Carolyn Rosé. 2021. FanfictionNLP: A text processing pipeline for fanfiction. In Proceedings of the Third Workshop on Narrative Understanding, pages 13–23, Virtual. Association for Computational Lingui… find
  44. Mo Yu, Yisi Sang, Kangsheng Pu, Zekai Wei, Han Wang, Jing Li, Yue Yu, and Jie Zhou. 2022. Few-shot character understanding in movies as an assessment to meta-learning of theory-of-mind. arXiv preprint arXiv:2211.04684. — [arXiv:2211.04684](https://arxiv.org/abs/2211.04684) find
  45. Liu Zhuang, Lin Wayne, Shi Ya, and Zhao Jun. 2021. A robustly optimized BERT pre-training approach with post-training. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 1218–1227, Huhhot, China. Chinese Information Processing Society of China. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/baruah-2023-character-coreference-resolution-movie-screenplays/