The Nuts and Bolts of Conceptual Blending: Multidomain Concept Creation with Divago

Martins, Pedro; Pereira, Francisco C.; Cardoso, F. Amílcar

doi:10.1007/978-3-319-43610-4_5

Cited by 5 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite some issues that make it challenging to implement systems based on this theory without introducing additional constraints (Veale, 2019;Li et al, 2012), conceptual blending has been very influential in computational creativity research. Divago (Martins et al, 2019), for example, is a system for automatically blending two different domains among those that are present in its knowledge base. As an example, working on the concepts of ''horse'' and ''bird'', depending on which element of the two domains are mapped together, it can generate new animals such as a winged horse, a horse that flies by using its ears as wings, or a ''transporter bird'' that looks like a bird but can carry humans and be used for cargo and traction.…”

Section: Optimal Innovationmentioning

confidence: 99%

Pragmatic evaluations of automated linguistic creativity

Gatti

Stock²,

Strapparava³

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

The optimal innovation hypothesis (OIH) offers a good aesthetic and cognitive reference for the kind of linguistic creativity where minimal variations can have a strong effect on the audience and realize an overall intended goal. The same approach can be the basis for creative systems. The question is how to concretely evaluate not only their quality, but also their pragmatic effect. This paper describes the original evaluations of two systems based on the OIH, one automatically yielding witty headlines for incoming news, the other producing song parodies, varying the song lyrics to evoke a given concept. The goal is to bring attention to the importance of evaluating the pragmatic potential of creative systems, in addition to the quality of their output, and to demonstrate how such evaluations can be done.

show abstract

Section: Optimal Innovationmentioning

confidence: 99%

Pragmatic evaluations of automated linguistic creativity

Gatti

Stock²,

Strapparava³

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…In particular, six principles have been modeled: Integration, Topology, Unpacking, Maximization/Intensification of Vital Relations, Web and Relevance. For each of them, a measure is provided (see [8] for details). The fitness of each blend is measured as a weighted sum of the individual measured values.…”

Section: The Blendfactorymentioning

confidence: 99%

“…However, it should be noted that this series of experiments does not include an evaluation of the different compositions in terms of the quality of the artifacts produced. For this type of evaluation, we refer the reader to previous works where comprehensive evaluations were performed [3,8,33,34].…”

Section: Experiments With Divagoflowmentioning

confidence: 99%

“…The current research in CC comprises not only various computational systems based on different cognitive theories related to creativity, such as bisociation and conceptual blending [1][2][3][4][5][6][7][8][9], but also evaluation methods to assess the quality of the aforementioned systems [10]. As for application domains, the research has been addressing different areas, including visual arts [11,12], music [13], poetry [14,15], and mathematics [16].…”

Section: Introductionmentioning

confidence: 99%

“…The theory also provides a set of consistent principles as well as a terminology that can be used in creativity modeling. As a result, the CB framework has been the basis for a few artificial creative systems [1][2][3][4][5][6][7][8].…”

Section: Brief Introduction To Conceptual Blendingmentioning

confidence: 99%

See 2 more Smart Citations

Computational creativity infrastructure for online software composition: A conceptual blending use case

et al. 2019

Self Cite

View full text Add to dashboard Cite

Computational Creativity [CC] is a multidisciplinary research field, studying how to engineer software that exhibits behavior which would reasonably be deemed creative. This article shows how composition of software solutions in this field can effectively be supported through a CC infrastructure that supports user-friendly development of CC software components and workflows, their sharing, execution and reuse. The infrastructure allows CC researchers to build workflows that can be executed online and be easily reused by others through the workflow web address. Moreover, it enables the building of procedures composed of software developed by different researchers from different laboratories, leading to novel ways of software composition for computational purposes that were not expected in advance. This capability is illustrated on a workflow that implements a Concept Generator prototype based on the Conceptual Blending framework. The prototype consists of a composition of modules made available as web services, and is explored and tested through experiments involving blending of texts from different domains, blending of images, and poetry generation.

show abstract

Autonomous Composition as Search in a Conceptual Space: A Computational Creativity View

Cardoso

2018

Music Technology With Swing

View full text Add to dashboard Cite

The Nuts and Bolts of Conceptual Blending: Multidomain Concept Creation with Divago

Cited by 5 publications

References 0 publications

Pragmatic evaluations of automated linguistic creativity

Pragmatic evaluations of automated linguistic creativity

Computational creativity infrastructure for online software composition: A conceptual blending use case

Autonomous Composition as Search in a Conceptual Space: A Computational Creativity View

Contact Info

Product

Resources

About