Poetry generation with PoeTryMe



PoeTryMe is a platform for the automatic generation of poetry, with a versatile architecture that provides a high level of customisation. The user can define features that go from the poem configuration and the line templates, to the initial seed words that will define a generation domain, and also the generation strategy. In this chapter, we introduce PoeTryMe’s architecture and describe how we used it to generate poetry in Portuguese, using natural language processing resources for this language as well as patterns that denote semantic relations in human-created poetry. After presenting the resources used with PoeTryMe, the problem of poetry generation is tackled incrementally, as our decisions are explained and illustrated, step-by-step. In the end, the objective features of the poems generated by the implemented strategies are compared, while the best-scoring poems are shown.


computational creativity, linguistic creativity, poetry generation


Computational Creativity, Poetry Generation

Book Chapter

Computational Creativity Research: Towards Creative Machines, 12, pp. 243-266, Springer/Atlantis Press, January 2015


Cited by

Year 2017 : 3 citations

 Astigarraga, A., Martínez-Otzeta, J. M., Rodriguez, I., Sierra, B., and Lazkano, E. (2017). Markov text generator for Basque poetry. In Proceedings of 20th International Conference on Text, Speech, and Dialogue, TSD 2017, volume 10415 of LNCS, pages 228–236. Springer.

 Astigarraga, A., Martnez-Otzeta, J. M., Rodriguez, I., Sierra, B., and Lazkano, E. (2017). Emotional poetry generation. In Proceedings of 19th International Conference on Speech and Computer, SPECOM 2017, Hatfield, UK, volume 10458 of LNCS. Springer, Cham.

 Astigarraga, A., María Martínez-Otzeta, J., Rodriguez Rodriguez, I., Sierra, B., and Lazkano, E. (2017). Poet’s little helper: A methodology for computer-based poetry generation. a case study for the basque language. In Proceedings of the Workshop on Computational Creativity in Natural Language Generation (CC-NLG 2017), pages 2–10, Santiago de Compostela, Spain. Association for Computational Linguistics.

Year 2016 : 2 citations

 Graefe, A., Haim, M., Haarmann, B., and Brosius, H.-B. (2016). Readers perception of computer-generated news: Credibility, expertise, and readability. Journalism. (published online on April 2016).

 Zaidan, T. and Goes, L. F. W. (2016). Evolvestone: An evolutionary generator of balanced digital collectible card games. In Proceedings of XV Simpósio Brasileiro de Jogos e Entretimento Digital, SBGames, pages 11–17, São Paulo, SP, Brazil.

Year 2015 : 1 citations

 Graefe, A., Haim, M., Haarmann, B., and Brosius, H.-B. (2015). Perception of automated computer-generated news: Credibility, expertise, and readability. In 11th Dubrovnik Media Conference Days: Artificial Intelligence, Robots, and Media, Dubrovnik, Croatia.