Generating Modern Poetry Automatically in Finnish

Mika Hämäläinen, Khalid Alnajjar


Abstract
We present a novel approach for generating poetry automatically for the morphologically rich Finnish language by using a genetic algorithm. The approach improves the state of the art of the previous Finnish poem generators by introducing a higher degree of freedom in terms of structural creativity. Our approach is evaluated and described within the paradigm of computational creativity, where the fitness functions of the genetic algorithm are assimilated with the notion of aesthetics. The output is considered to be a poem 81.5% of the time by human evaluators.
Anthology ID:
D19-1617
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5999–6004
Language:
URL:
https://aclanthology.org/D19-1617
DOI:
10.18653/v1/D19-1617
Bibkey:
Cite (ACL):
Mika Hämäläinen and Khalid Alnajjar. 2019. Generating Modern Poetry Automatically in Finnish. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5999–6004, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Generating Modern Poetry Automatically in Finnish (Hämäläinen & Alnajjar, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/D19-1617.pdf