Abstract
Automatic generation of linguistic artifacts is a problem that has been sporadically tackled over the years. The main goal of this paper is to explore how concept associations can be useful from a computational creativity point of view to generate some of these artifacts. We present an approach where finding associations between concepts that would not usually be considered as related (for example life and politics or diamond and concrete) could be the seed for the generation of creative and surprising linguistic artifacts such as rhetorical figures (life is like politics) and riddles (what is as hard as concrete?). Human volunteers evaluated the quality and appropriateness of the generated figures and riddles, and the results show that the concept associations obtained are useful for producing these kinds of creative artifacts.
Highlights
IntroductionOne of the most remarkable passages in The Hobbit (Tolkien, 1937) takes place in the riddle competition between Bilbo and Gollum, with one of the trickiest riddles being: Voiceless it cries, Wingless flutters, Toothless bites, Mouthless mutters.It is noteworthy to see how each verse transfers some properties from other entities to the solution of the riddle - the wind - in such a way that it makes it look amazingly enigmatic.The possibility to transfer similar properties between concepts from different domains is a literary resource that has been exploited by writers all over the years, even before Aristotle defined metaphors as “giving the thing a name that belongs to something else; the transference being either from genus to species, or from species to genus, or from species to species, or on grounds of analogy.” computational approaches to riddle or rhetorical figure generation have not explicitly made extensive use of this mechanism in order to create literary artifacts
The general obtained mean is 4 (3.19 for those of different categories and 4.20 for those belonging to the same category) which indicates that the process we have used to generate the rhetorical figures works quite well when concepts of the same category are used, according to the opinions of the evaluators, something happens in the case of using concepts that belong to different categories, which, in general, obtain worse results
We can conclude that the results of the curated version of the riddles are better than the ones of the original set, which suggests that an additional selection of comparisons is needed in some cases in order to improve the quality of the generated riddles
Summary
One of the most remarkable passages in The Hobbit (Tolkien, 1937) takes place in the riddle competition between Bilbo and Gollum, with one of the trickiest riddles being: Voiceless it cries, Wingless flutters, Toothless bites, Mouthless mutters.It is noteworthy to see how each verse transfers some properties from other entities to the solution of the riddle - the wind - in such a way that it makes it look amazingly enigmatic.The possibility to transfer similar properties between concepts from different domains is a literary resource that has been exploited by writers all over the years, even before Aristotle defined metaphors as “giving the thing a name that belongs to something else; the transference being either from genus to species, or from species to genus, or from species to species, or on grounds of analogy.” computational approaches to riddle or rhetorical figure generation have not explicitly made extensive use of this mechanism in order to create literary artifacts. It is noteworthy to see how each verse transfers some properties from other entities to the solution of the riddle - the wind - in such a way that it makes it look amazingly enigmatic. The possibility to transfer similar properties between concepts from different domains is a literary resource that has been exploited by writers all over the years, even before Aristotle defined metaphors as “giving the thing a name that belongs to something else; the transference being either from genus to species, or from species to genus, or from species to species, or on grounds of analogy.”. Computational approaches to riddle or rhetorical figure generation have not explicitly made extensive use of this mechanism in order to create literary artifacts. Concept relations have proved to be useful for rhetorical figure analysis but have not been explored in depth for rhetorical figure generation, for example.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
