A Preliminary Study for Literary Rhyme Generation based on Neuronal Representation, Semantics and Shallow Parsing

TL;DR

This paper presents a novel model for generating Spanish literary rhymes by integrating language structures and neural networks, with promising initial evaluation results.

Contribution

It introduces a new approach combining linguistic structures and neural networks for Spanish rhyme generation, which is a novel contribution.

Findings

Encouraging results from manual evaluation of generated texts.

Successful integration of language structures and neural models for rhyme generation.

Abstract

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.