AI-Powered Poetry Generation with Author Linguistic Style Transfer

The application of artificial neural networks to the problem of style transfer has been implemented successfully for paintings by Gatys, Ecker, and Bethge (2015). Linguistic style transfer for prose works has been recently explored for example in Ficler and Goldberg (2017), Xu et al. (2012).

This project, which culminated in BACON1, adapted a generic poetry generator from Hopkins and Kiela (2017) with the addition of concepts from these other papers to capture an author’s specific writing style and emulate it through an automated poetry generator.


      Ficler, J., Goldberg, Y. (2017). Controlling linguistic style aspects in neural language generation. ArXiv Preprint, ArXiv:1707.02633 [Cs.CL].

      Gatys, L. A., Ecker, A. S., Bethge, M. (2015). A Neural Algorithm of Artistic Style. ArXiv Preprint, ArXiv:1508.06576 [Cs.CV].

      Hopkins, J., Kiela, D. (2017). Automatically Generating Rhythmic Verse with Neural Networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 1, pp. 168–178).

      Xu, W., Ritter, A., Dolan, B., Grishman, R., Cherry, C. (2012). Paraphrasing for style. Proceedings of COLING 2012, 2899–2914.

1 BACON stands for Basic AI for Collaborative pOetry writiNg. The name is coined after Sir Francis Bacon who, according to some, was who actually wrote William Shakespeare’s plays.

Alejandro Rodriguez Pascual
Alejandro Rodriguez Pascual
Master’s of Science in Computer Science - Specialization in Data Science

Recently completed my M.S. in Computer Science (Data Science Specialization) at the University of Massachusetts, Amherst.