Abstract
This article presents a series of experiments in automatically generating poetic texts. We confined our attention to the generation of texts which are syntactically well-formed, meet certain pre-specified patterns of metre and broadly convey some given meaning. Such aspects can be formally defined, thus avoiding the complications of imagery and interpretation that are central to assessing more free forms of verse. Our implemented system, McGONAGALL, applies the genetic algorithm to construct such texts. It uses a sophisticated linguistic formalism to represent its genomic information, from which can be computed the phenotypic information of both semantic representations and patterns of stress. The conducted experiments broadly indicated that relatively meaningful text could be produced if the constraints on metre were relaxed, and precise metric text was possible with loose semantic constraints, but it was difficult to produce text which was both semantically coherent and of high quality metrically.
Original language | English |
---|---|
Pages (from-to) | 43–64 |
Number of pages | 22 |
Journal | Journal of Experimental & Theoretical Artificial Intelligence |
Volume | 24 |
Issue number | 1 |
Early online date | 20 Jan 2012 |
DOIs | |
Publication status | Published - 20 Jan 2012 |
Bibliographical note
Work carried out when all authors were at the University of Edinburgh.Keywords
- natural language generation
- genetic algorithms
- poetry
- creative language