A Preliminary Study for Literary Rhyme Generation based on Neuronal Representation, Semantics and Shallow Parsing
This addresses the challenge of computational creativity in poetry generation for Spanish, but it is incremental as it builds on existing methods like Word2vec.
The paper tackled the problem of generating literary rhymes in Spanish by combining language structures and neural network models, and reported encouraging results from a manual evaluation.
In recent years, researchers in the area of Computational Creativity have studied the human creative process proposing different approaches to reproduce it with a formal procedure. In this paper, we introduce a model for the generation of literary rhymes in Spanish, combining structures of language and neural network models %(\textit{Word2vec}).%, into a structure for semantic assimilation. The results obtained with a manual evaluation of the texts generated by our algorithm are encouraging.