Skip to main content
    • Aa
    • Aa

Multilingual extension and evaluation of a poetry generator*


Poetry generation is a specific kind of natural language generation where several sources of knowledge are typically exploited to handle features on different levels, such as syntax, semantics, form or aesthetics. But although this task has been addressed by several researchers, and targeted different languages, all known systems have focused on a limited purpose and a single language. This article describes the effort of adapting the same architecture to generate poetry in three different languages – Portuguese, Spanish and English. An existing architecture is first described and complemented with the adaptations required for each language, including the linguistic resources used for handling morphology, syntax, semantics and metric scansion. An automatic evaluation was designed in such a way that it would be applicable to the target languages. It covered three relevant aspects of the generated poems, namely: the presence of poetic features, the variation of the linguistic structure and the semantic connection to a given topic. The automatic measures applied for the second and third aspect can be seen as novel in the evaluation of poetry. Overall, poems were successfully generated in the three languages addressed. Despite minor differences in different languages or seed words, poems revealed to have a regular metre, frequent rhymes, to exhibit an interesting degree of variation, and to be semantically-associated with the initially given seeds.

Hide All

This work was supported by projects PROSECCO and ConCreTe. Part of this work was developed during short term visits funded by the PROSECCO CSA project, European Commission under FP7 FET grant number 600653. The project ConCreTe acknowledges the financial support of the Future and Emerging Technologies (FET) programme within the Seventh Framework Programme for Research of the European Commission, under FET grant number 611733.

Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

P. Gervás 2001. An expert system for the composition of formal Spanish poetry. Journal of Knowledge-Based Systems 14 (3–4): 181–8.

H. Gonçalo Oliveira , 2016. Automatic generation of poetry inspired by Twitter trends. In Knowledge Discovery, Knowledge Engineering and Knowledge Management (Post-conference Proceedings of IC3K — Revised Selected Papers), CCIS, vol. 631, Springer, pp. 1327.

A. Jordanous 2012. A standardised procedure for evaluating creative systems: computational creativity evaluation based on what it is to be creative. Cognitive Computation 4 (3): 246–79.

B. Liu , M. Hu , and J. Cheng , 2005. Opinion observer: analyzing and comparing opinions on the Web. In Proceedings of the 14th International Conference on World Wide Web, WWW '05, New York, NY, USA, ACM, pp. 342–51.

E. Malmi , P. Takala , H. Toivonen , T. Raiko , and A. Gionis , 2016. DopeLearning: a computational approach to rap lyrics generation. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13–17, 2016, pp. 195204.

Y. Netzer , D. Gabay , Y. Goldberg , and M. Elhadad , 2009. Gaiku: generating haiku with word associations norms. In Proceedings of the Workshop on Computational Approaches to Linguistic Creativity, CALC’09, Stroudsburg, PA, USA: ACL Press, pp. 32–9.

A. A. Ramakrishnan , S. Kuppan , and S. L. Devi , 2009. Automatic generation of Tamil lyrics for melodies. In Proceedings of the Workshop on Computational Approaches to Linguistic Creativity, CALC’09, Stroudsburg, PA, USA: ACL Press, pp. 40–6.

E. Reiter , and R. Dale , 2000. Building Natural Language Generation Systems. New York, USA: Cambridge University Press.

M. J. Silva , P. Carvalho , and L. Sarmento , 2012. Building a sentiment lexicon for social judgement mining. In Proceedings of Computational Processing of the Portuguese Language – 10th International Conference (PROPOR 2012), LNCS, vol. 7243, Coimbra, Portugal, Springer, pp. 218–28.

P. D. Turney , 2001. Mining the web for synonyms: PMI–IR versus LSA on TOEFL. In Proceedings of 12th European Conference on Machine Learning, ECML 2001, LNCS, vol. 2167, London, UK: Springer, pp. 491502.

A. Valitutti , A. Doucet , J. Toivanen , and H. Toivonen 2016. Computational generation and dissection of lexical replacement humor. Natural Language Engineering 22 (5): 123.

X. Zhang , and M. Lapata , 2014. Chinese poetry generation with recurrent neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, Stroudsburg, PA, USA: ACL Press, pp. 670–80.

Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Natural Language Engineering
  • ISSN: 1351-3249
  • EISSN: 1469-8110
  • URL: /core/journals/natural-language-engineering
Please enter your name
Please enter a valid email address
Who would you like to send this to? *


Full text views

Total number of HTML views: 8
Total number of PDF views: 40 *
Loading metrics...

Abstract views

Total abstract views: 190 *
Loading metrics...

* Views captured on Cambridge Core between 1st June 2017 - 22nd September 2017. This data will be updated every 24 hours.