Abstract
Automatic poetry generation is novel and interesting application of natural language processing research. It became more popular during the last few years due to the rapid development of technology and neural computing power. This line of research can be applied to the study of linguistics and literature, for social science experiments, or simply for entertainment. The most effective known method of artificial poem generation uses recurrent neural networks (RNN). We also used RNNs to generate poems in the style of Adam Mickiewicz. Our network was trained on the ‘Sir Thaddeus’ poem. For data pre-processing, we used a specialized stemming tool, which is one of the major innovations and contributions of this work. Our experiment was conducted on the source text, divided into sub-word units (at a level of resolution close to syllables). This approach is novel and is not often employed in the published literature. The sub-words units seem to be a natural choice for analysis of the Polish language, as the language is morphologically rich due to cases, gender forms and a large vocabulary. Moreover, ‘Sir Thaddeus’ contains rhymes, so the analysis of syllables can be meaningful. We verified our model with different settings for the temperature parameter, which controls the randomness of the generated text. We also compared our results with similar models trained on the same text but divided into characters (which is the most common approach alongside the use of full word units). The differences were tremendous. Our solution generated much better poems that were able to follow the metre and vocabulary of the source data text.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Milosz, C.: The History of Polish Literature. University of California Press (1983)
Tikhonov, A., Yamshchikov, I.P.: Guess who? Multilingual approach for the automated generation of author-stylized poetry. arXiv preprint arXiv:1807.07147 (2018)
Liu, B., Fu, J., Kato, M.P., Yoshikawa, M.: Beyond narrative description: generating poetry from images by multi-adversarial training. arXiv preprint arXiv:1804.08473 (2018)
Cheng, W.F., Wu, C.C., Song, R., Fu, J., Xie, X., Nie, J.Y.: Image inspired poetry generation in XiaoIce. arXiv preprint arXiv:1808.03090 (2018)
Lamb, C., Brown, D.G., Clarke, C.L.: A taxonomy of generative poetry techniques. J. Math. Arts 11(3), 159–179 (2017)
Oliveira, H.: Automatic Generation of Poetry: An Overview. Universidade de Coimbra (2009)
Gervás, P.: Exploring quantitative evaluations of the creativity of automatic poets. In: Workshop on Creative Systems, Approaches to Creativity in Artificial Intelligence and Cognitive Science, 15th European Conference on Artificial Intelligence, Lyon, France. IOS Press (2002)
Zhang, J., Feng, Y., Wang, D., Wang, Y., Abel, A., Zhang, S., Zhang, A.: Flexible and creative Chinese poetry generation using neural memory. arXiv preprint arXiv:1705.03773 (2017)
Loller-Andersen, M., Gambäck, B.: Deep Learning-Based Poetry Generation Given Visual Input
Hopkins, J., Kiela, D.: Automatically generating rhythmic verse with neural networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 168–178 (2017)
Wołk, A., Wołk, K., Marasek, K.: Analysis of complexity between spoken and written language for statistical machine translation in West-Slavic group. In Multimedia and Network Information Systems, pp. 251–260. Springer, Cham (2017)
Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464–472. IEEE, March 2017
Wolk, K., Marasek, K.: Survey on neural machine translation into polish. In: International Conference on Multimedia and Network Information System, pp. 260–272. Springer, Cham, online tool version, September 2018 http://ld.clarin-pl.eu:5000
Collings, M.R.: Stephen King as Richard Bachman, p. 168. Starmont House (1985)
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Berlin, Germany (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 328–339 (2018)
Tillmann, C., Ney, H.: Word reordering and a dynamic programming beam search algorithm for statistical machine translation. Comput. Linguist. 29(1), 97–133 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wołk, K., Zawadzka-Gosk, E., Czarnowski, W. (2019). Deep Learning and Sub-Word-Unit Approach in Written Art Generation. In: Rocha, Á., Adeli, H., Reis, L., Costanzo, S. (eds) New Knowledge in Information Systems and Technologies. WorldCIST'19 2019. Advances in Intelligent Systems and Computing, vol 930. Springer, Cham. https://doi.org/10.1007/978-3-030-16181-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-16181-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16180-4
Online ISBN: 978-3-030-16181-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)