Constrained creation of poetic forms during theme-driven exploration of a domain defined by an N-gram model

ABSTRACT Most poetry-generation systems apply opportunistic approaches where algorithmic procedures are applied to explore the conceptual space defined by a given knowledge resource in search of solutions that might be aesthetically valuable. Aesthetical value is assumed to arise from compliance to a given poetic form – such as rhyme or metrical regularity – or from evidence of semantic relations between the words in the resulting poems that can be interpreted as rhetorical tropes – such as similes, analogies, or metaphors. This approach tends to fix a priori the aesthetic parameters of the results, and imposes no constraints on the message to be conveyed. The present paper describes an attempt to initiate a shift in this balance, introducing means for constraining the output to certain topics and allowing a looser mechanism for constraining form. This goal arose as a result of the need to produce poems for a themed collection commissioned to be included in a book. The solution adopted explores an approach to creativity where the goals are not solely aesthetic and where the results may be surprising in their poetic form. An existing computer poet, originally developed to produce poems in a given form but with no specific constraints on their content, is put to the task of producing a set of poems with explicit restrictions on content, and allowing for an exploration of poetic form. Alternative generation methods are devised to overcome the difficulties, and the various insights arising from these new methods and the impact they have on the set of resulting poems are discussed in terms of their potential contribution to better poetry-generation systems.

[1]  Ruli Manurung,et al.  Pemuisi: a constraint satisfaction-based generator of topical Indonesian poetry , 2014, ICCC.

[2]  Pablo Gervás,et al.  Reading and Writing as a Creative Cycle: the Need for a Computational Model , 2014, ICCC.

[3]  Hannu Toivonen,et al.  Harnessing Constraint Programming for Poetry Composition , 2013, ICCC.

[4]  Hugo Gonçalo Oliveira PoeTryMe : a versatile platform for poetry generation , 2012 .

[5]  Tony Veale,et al.  Less Rhyme, More Reason: Knowledge-based Poetry Generation with Feeling, Insight and Wit , 2013, ICCC.

[6]  Pablo Gervás Computational Modelling of Poetry Generation , 2013 .

[7]  Pablo Gervás Dynamic Inspiring Sets for Sustained Novelty in Poetry Generation , 2011, ICCC.

[8]  Pablo Gervás,et al.  WASP: Evaluation of Different Strategies for the Automatic Generation of Spanish Verse , 2002 .

[9]  Simon Colton,et al.  Full-FACE Poetry Generation , 2012, ICCC.

[10]  Oulipo Atlas de littérature potentielle , 1981 .

[11]  Amitava Das,et al.  Poetic Machine: Computational Creativity for Automatic Poetry Generation in Bengali , 2014, ICCC.

[12]  H. Manurung An evolutionary algorithm approach to poetry generation , 2004 .

[13]  François Pachet,et al.  Markov Constraints for Generating Lyrics with Style , 2012, ECAI.

[14]  Simon Colton,et al.  Computational Creativity: The Final Frontier? , 2012, ECAI.

[15]  Hannu Toivonen,et al.  The Officer Is Taller Than You, Who Race Yourself! Using Document Specific Word Associations in Poetry Generation , 2014, ICCC.

[16]  Bipin Indurkhya,et al.  Poetry generation system with an emotional personality , 2014, ICCC.

[17]  Brent D. Rosso Creativity and Constraints: Exploring the Role of Constraints in the Creative Processes of Research and Development Teams , 2014 .

[18]  M. Boden The creative mind : myths & mechanisms , 1991 .

[19]  T. Dalrymple The death of the author , 2008, BMJ : British Medical Journal.

[20]  Manex Agirrezabal,et al.  POS-Tag Based Poetry Generation with WordNet , 2013, ENLG.

[21]  Simon Colton,et al.  The FloWr Framework: Automated Flowchart Construction, Optimisation and Alteration for Creative Systems , 2014, ICCC.

[22]  Hannu Toivonen,et al.  Corpus-Based Generation of Content and Form in Poetry , 2012, ICCC.

[23]  Graeme Ritchie,et al.  Some Empirical Criteria for Attributing Creativity to a Computer Program , 2007, Minds and Machines.

[24]  Geraint A. Wiggins Searching for computational creativity , 2006, New Generation Computing.