Computational Understanding, Generation and Evaluation of Creative Expressions

Show full item record



Permalink

http://urn.fi/URN:ISBN:978-951-51-7146-7
Title: Computational Understanding, Generation and Evaluation of Creative Expressions
Author: Alnajjar, Khalid
Contributor: University of Helsinki, Faculty of Science, Department of Computer Science
Doctoral Programme in Computer Science
Publisher: Helsingin yliopisto
Date: 2021-03-22
Language: en
URI: http://urn.fi/URN:ISBN:978-951-51-7146-7
http://hdl.handle.net/10138/327256
Thesis level: Doctoral dissertation (article-based)
Abstract: Computational creativity has received a good amount of research interest in generating creative artefacts programmatically. At the same time, research has been conducted in computational aesthetics, which essentially tries to analyse creativity exhibited in art. This thesis aims to unite these two distinct lines of research in the context of natural language generation by building, from models for interpretation and generation, a cohesive whole that can assess its own generations. I present a novel method for interpreting one of the most difficult rhetoric devices in the figurative use of language: metaphors. The method does not rely on hand-annotated data and it is purely data-driven. It obtains the state of the art results and is comparable to the interpretations given by humans. We show how a metaphor interpretation model can be used in generating metaphors and metaphorical expressions. Furthermore, as a creative natural language generation task, we demonstrate assigning creative names to colours using an algorithmic approach that leverages a knowledge base of stereotypical associations for colours. Colour names produced by the approach were favoured by human judges to names given by humans 70% of the time. A genetic algorithm-based method is elaborated for slogan generation. The use of a genetic algorithm makes it possible to model the generation of text while optimising multiple fitness functions, as part of the evolutionary process, to assess the aesthetic quality of the output. Our evaluation indicates that having multiple balanced aesthetics outperforms a single maximised aesthetic. From an interplay of neural networks and the traditional AI approach of genetic algorithms, we present a symbiotic framework. This is called the master-apprentice framework. This makes it possible for the system to produce more diverse output as the neural network can learn from both the genetic algorithm and real people. The master-apprentice framework emphasises a strong theoretical foundation for the creative problem one seeks to solve. From this theoretical foundation, a reasoned evaluation method can be derived. This thesis presents two different evaluation practices based on two different theories on computational creativity. This research is conducted in two distinct practical tasks: pun generation in English and poetry generation in Finnish.Laskennallista luovuutta on tutkittu paljon puhtaan tuottamisen näkökulmasta ja saman aikaan tutkimusta on tehty laskennallisen estetiikan saralla. Väitöskirjani yhdistää näitä kahta eri koulukuntaa, sillä kehittämäni laskennallisesti luovat järjestelmät käyttävät tuottamisessa apuna estetiikkaa; järjestelmät siis tulkitsevat teoksiaan samaan aikaan, kun ne niitä tuottavat. Käsittelen väitöskirjassani metaforien automaattista tulkintaa, värien nimien tuottamista, sloganien tuottamista sekä suomenkielisen runouden tuottamista. Metodeina käytän perinteistä koneoppimisalgoritmia, eli niin kutsuttua geneettistä algoritmia, sekä neuroverkkoja. Niiden yhdistelmää nimitän mestari ja oppipoika -malliksi, jossa geneettinen algoritmi opettaa neuroverkkoja.
Subject: computer Science
Rights: This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.


Files in this item

Total number of downloads: Loading...

Files Size Format View
alnajjar_khalid_dissertation_2021.pdf 321.3Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record