Literary Natural Language Generation with Psychological Traits

Abstract

The area of Computational Creativity has received much attention in recent years. In this paper, within this framework, we propose a model for the generation of literary sentences in Spanish, which is based on statistical algorithms, shallow parsing and the automatic detection of personality features of characters of well known literary texts. We present encouraging results of the analysis of sentences generated by our methods obtained with human inspection.

Automatic Generation of Literary Sentences in French

“…We have developed algorithms for the production of literary sentences in Spanish and Portuguese [6,[18][19][20][21] and, in this paper, we review some of their main features which we adapt here for the production of literary sentences in French. The algorithms of our ATG model use keywords (queries) provided by the user as a semantic guide that determines the semantic context of the phrases that are produced.…”

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

“…For this reason, we have performed a manual evaluation of our experiments, asking 6 people with a graduate degree in literature to evaluate the rhymes generated by our algorithm and their semantic relations. In previous general ATG models [Moreno-Jiménez et al 2020b, Moreno-Jiménez et al 2020a], criteria such as coherence and grammatical composition were evaluated. Here, we asked the evaluators to indicate if they perceived a rhyme between the last words of each sentence in a pair and also to specify their perception of the semantic relation between the two rhyming words, which could be one of the following: any relation, low relation, acceptable relation, good relation and strong relation.…”

“…In this paper, we introduce a model for the generation of rhymes with literary components. Our proposal is based on findings detailed in [Moreno-Jiménez et al 2020a], where Automatic Text Generation (ATG) techniques are combined with neural network (NN) based models, such as the Word2vec algorithm [Mikolov et al 2013b], for the generation of literary texts. In Section 2, we present some of the literature regarding literary text generation, focusing on methods related to this paper.…”

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

“…For this reason, we have performed a manual evaluation of our experiments, asking 6 people with a graduate degree in literature to evaluate the rhymes generated by our algorithm and their semantic relations. In previous general ATG models [12,11], criteria such as coherence and grammatical composition were evaluated. Here, we asked the evaluators to indicate if they perceived a rhyme between the last words of each sentence in a pair and also to specify their perception of the semantic relation between the two rhyming words, which could be one of the following: any relation, low relation, acceptable relation, good relation and strong relation.…”

“…In this paper, we introduce a model for the generation of rhymes with literary components. Our proposal is based on findings detailed in [11], where Automatic Text Generation (ATG) techniques are combined with neural network (NN) based models, such as the Word2vec algorithm [9], for the generation of literary texts. In Section 2, we present some of the literature regarding literary text generation, focusing on methods related to this paper.…”