Abstract
Poetry generation is becoming popular among researchers of Natural Language Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that may be regarded as poetry, poetry generation systems are typically knowledge-intensive and have to deal with several levels of language, from lexical to semantics. Interest on the topic resulted in the development of several poetry generators described in the literature, with different features covered or handled differently, by a broad range of alternative approaches, as well as different perspectives on evaluation, another challenging aspect due the underlying subjectivity. This paper surveys intelligent poetry generators around a set of relevant axis for poetry generation – targeted languages, form and content features, techniques, reutilisation of material, and evaluation – and aims to organise work developed on this topic so far.
Highlights
Interest in the development of automatic methods for generating poetry dates back to the 1960s, even before computers were accessible to everyone
Given the number of constraints involved in poetry generation, it is natural to have this problem formulated as a Constraint Satisfaction approach (Toivanen et al, 2013; Rashel and Manurung, 2014)
Poetry generation is becoming a mature research field, which is confirmed by several works that go beyond the production and exhibition of a few interesting poems that, to some extent, match the target goals
Summary
Interest in the development of automatic methods for generating poetry dates back to the 1960s, even before computers were accessible to everyone. Since the works of Gervas (2000) and Manurung (2003), the development of “intelligent” poetry generation systems has seen a significant increase These systems are not limited to rewriting text in a poetic form. Given the challenge involved and the range of possibilities, it is not surprising to see many poetry generators developed as serious research efforts where distinct approaches to tackle this common goal are explored, reported in scientific papers, with enough detail, and even compared to prior work. Instead of a full description of specific systems, it is organised around the identified axis and focuses on distinct ways they were handled by different systems For those interested on the topic, this can be seen as a quicker reference for selecting suitable approaches, possibly tackling their limitations, or opt instead for alternative approaches, novel for poetry generation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
