Advertisement

A Survey of Deep Learning Applied to Story Generation

  • Chenglong Hou
  • Chensong Zhou
  • Kun Zhou
  • Jinan SunEmail author
  • Sisi Xuanyuanj
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11910)

Abstract

With the rapid development of deep learning in the fields of text abstraction and dialogue generation, researchers are now reconsidering the long-standing story-generation task from the 1970s. Deep learning methods are gradually being adopted to solve problems in traditional story generation, making story generation a new research hotspot in the field of text generation. However, in the field of story generation, the widely used seq2seq model is unable to provide adequate long-distance text modeling. As a result, this model struggles to solve the story-generation task, since the relation between long text should be considered, and coherency and vividness are critical. Thus, recent years have seen numerous proposals for better modeling methods. In this paper, we present the results of a comprehensive study of story generation. We first introduce the relevant concepts of story generation, its background, and the current state of research. We then summarize and analyze the standard methods of story generation. Based on various divisions of user constraints, the story-generation methods are divided into three categories: the theme-oriented model, the storyline-oriented model, and the human-machine-interaction–oriented model. On this basis, we discuss the basic ideas and main concerns of various methods and compare the strengths and weaknesses of each method. Finally, we finish by analyzing and forecasting future developments that could push story-generation research toward a new frontier.

Keywords

Story generation Text generation Deep learning 

Notes

Acknowledgment

This work is supported by the National Key Research and Development Program of China (No. 2017YFB1400805).

References

  1. 1.
    Meehan, J.R.: TALE-SPIN, an interactive program that writes stories. IJCAI 77, 91–98 (1977)Google Scholar
  2. 2.
    Zhu, F., Cungen, C.: A survey of narrative generation approaches. J. Chin. Inf. Process. 27(3), 33–40 (2013)Google Scholar
  3. 3.
    Cavazza, M., Charles, F., Mead, S.J.: Character-based interactive storytelling. IEEE Intell. Syst. 17(4), 17–24 (2002)CrossRefGoogle Scholar
  4. 4.
    Pizzi, D.: Emotional planning for character-based interactive storytelling. Teesside University (2011)Google Scholar
  5. 5.
    Lebowitz, M.: Story-telling as planning and learning. Poetics 14(6), 483–502 (1985)CrossRefGoogle Scholar
  6. 6.
    Turner, S.R.: MINSTREL: a computer model of creativity and storytelling, pp. 1505–1505 (1994)Google Scholar
  7. 7.
    Bringsjord, S., Ferrucci, D.: Artificial Intelligence and Literary Creativity: Inside the Mind of Brutus, a Storytelling Machine. Psychology Press, Abingdon (1999)Google Scholar
  8. 8.
    Perez, R.P.Ý., Sharples, M.: MEXICA: a computer model of a cognitive account of creative writing. J. Exp. Theor. Artif. Intell. 13(2), 119–139 (2001)CrossRefGoogle Scholar
  9. 9.
    Riedl, M.O., Young, R.M.: Narrative planning: balancing plot and character. J. Artif. Intell. Res. 39(1), 217–268 (2010)CrossRefGoogle Scholar
  10. 10.
    Gervas, P., et al.: Story plot generation based on CBR. Knowl. Based Syst. 18(4), 235–242 (2005)CrossRefGoogle Scholar
  11. 11.
    Swanson, R., Gordon, A.S.: Say anything: using textual case-based reasoning to enable open-domain interactive storytelling. Ksii Trans. Internet Inf. Syst. 2(3), 16 (2012)Google Scholar
  12. 12.
    Li, B., et al.: Story generation with crowdsourced plot graphs. In: National Conference on Artificial Intelligence, pp. 598–604 (2013)Google Scholar
  13. 13.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Neural Information Processing Systems, pp. 3104–3112 (2014)Google Scholar
  14. 14.
    Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Empirical Methods in Natural Language Processing, pp. 1412–1421 (2015)Google Scholar
  15. 15.
    Martin, L.J., et al.: Event representations for automated story generation with deep neural nets. In: National Conference on Artificial Intelligence, pp. 868–875 (2018)Google Scholar
  16. 16.
    Li, J., et al.: Deep reinforcement learning for dialogue generation. In: Empirical Methods in Natural Language Processing, pp. 1192–1202 (2016)Google Scholar
  17. 17.
    Yao, L., et al: Plan-and-write: towards better automatic storytelling. In: National Conference on Artificial Intelligence (2019)Google Scholar
  18. 18.
    Guan, J., Wang, Y., Huang, M.: Story ending generation with incremental encoding and commonsense knowledge. In: National Conference on Artificial Intelligence (2019)Google Scholar
  19. 19.
    Tambwekar, P., et al.: Controllable neural story generation via reinforcement learning. arXiv: Computation and Language (2018)Google Scholar
  20. 20.
    Fan, A., Lewis, M., Dauphin, Y.N.: Hierarchical neural story generation. In: Meeting of the Association for Computational Linguistics, pp. 889–898 (2018)Google Scholar
  21. 21.
    Xu, J., et al.: A skeleton-based model for promoting coherence among sentences in narrative story generation.  In: Empirical Methods in Natural Language Processing, pp. 4306–4315 (2018)Google Scholar
  22. 22.
    Nayak, N., et al.: To plan or not to plan? Discourse planning in slot-value informed sequence to sequence models for language generation. In: Conference of the International Speech Communication Association, pp. 3339–3343 (2017)Google Scholar
  23. 23.
    Wang, Z., et al.: Chinese poetry generation with planning based neural network. In: International Conference on Computational Linguistics, pp. 1051–1060 (2016)Google Scholar
  24. 24.
    Mou, L., et al.: Sequence to backward and forward sequences: a content-introducing approach to generative short-text conversation. In: International Conference on Computational Linguistics, pp. 3349–3358 (2016)Google Scholar
  25. 25.
    Fan, A., Lewis, M., Dauphin, Y.: Strategies for structuring story generation. arXiv: Computation and Language (2019)Google Scholar
  26. 26.
    Huang, K., et al.: Visual storytelling. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1233–1239 (2016)Google Scholar
  27. 27.
    Wang, X., et al.: No metrics are perfect: adversarial reward learning for visual storytelling. In: Meeting of the Association for Computational Linguistics, pp. 899–909 (2018)Google Scholar
  28. 28.
    Kim, T., et al.: GLAC Net: GLocal attention cascading networks for multi-image cued story generation. arXiv: Computation and Language (2018)Google Scholar
  29. 29.
    Huang, Q., et al.: Hierarchically structured reinforcement learning for topically coherent visual story generation. In: National Conference on Artificial Intelligence (2019)Google Scholar
  30. 30.
    Li, J., Luong, T., Jurafsky, D.: A hierarchical neural autoencoder for paragraphs and documents. In: International Joint Conference on Natural Language Processing, pp. 1106–1115 (2015)Google Scholar
  31. 31.
    Yarats, D., Lewis, M.: Hierarchical text generation and planning for strategic dialogue. In: International Conference on Machine Learning, pp. 5587–5595 (2018)Google Scholar
  32. 32.
    Mostafazadeh, N., et al.: CaTeRS: causal and temporal relation scheme for semantic annotation of event structures. In: North American Chapter of the Association for Computational Linguistics, pp. 51–61 (2016)Google Scholar
  33. 33.
    Zhou, D., Guo, L., He, Y.: Neural storyline extraction model for storyline generation from news articles. In: North American Chapter of the Association for Computational Linguistics, pp. 1727–1736 (2018)Google Scholar
  34. 34.
    Jain, P., et al.: Story generation from sequence of independent short descriptions. arXiv: Computation and Language (2017)Google Scholar
  35. 35.
    Zhao, Y., et al.: From plots to endings: a reinforced pointer generator for story ending generation. In: International Conference Natural Language Processing, pp. 51–63 (2018)CrossRefGoogle Scholar
  36. 36.
    Clark, E.A., et al.: Creative writing with a machine in the loop: case studies on slogans and stories. In: Intelligent User Interfaces, pp. 329–340 (2018)Google Scholar
  37. 37.
    Peng, N., et al.: Towards controllable story generation. In: Proceedings of the First Workshop on Storytelling (2018)Google Scholar
  38. 38.
    Goldfarb-Tarrant, S., Feng, H., Peng, N.: Plan, write, and revise: an interactive system for open-domain story generation. arXiv: Computation and Language (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Chenglong Hou
    • 1
    • 2
  • Chensong Zhou
    • 3
  • Kun Zhou
    • 2
  • Jinan Sun
    • 1
    Email author
  • Sisi Xuanyuanj
    • 4
  1. 1.National Engineering Research Center for Software EngineeringPeking UniversityBeijingChina
  2. 2.School of Software and MicroelectronicsPeking UniversityBeijingChina
  3. 3.Potevio Information Technology Co., Ltd.BeijingChina
  4. 4.Department of Science and Technology of Shandong ProvinceJinanChina

Personalised recommendations