Nodebox compound doesnt take color5/16/2023 ![]() ![]() The method for generating slogans extracts skeletons from existing slogans. Additionally, a key component in our approach is a novel method for generating nominal metaphors, using a metaphor interpretation model, to allow generating metaphorical slogans. In this paper, we describe a novel method for automatically generating slogans, given a target concept (e.g., car) and an adjectival property to express (e.g., elegant) as input. Creating effective slogans is a resource-consuming task for humans. In advertising, slogans are used to enhance the recall of the advertised product by consumers and to distinguish it from others in the market. This research is conducted in two distinct practical tasks: pun generation in English and poetry generation in Finnish. This thesis presents two different evaluation practices based on two different theories on computational creativity. From this theoretical foundation, a reasoned evaluation method can be derived. The master-apprentice framework emphasises a strong theoretical foundation for the creative problem one seeks to solve. 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. This is called the master-apprentice framework. ![]() Our evaluation indicates that having multiple balanced aesthetics outperforms a single maximised aesthetic.įrom an interplay of neural networks and the traditional AI approach of genetic algorithms, we present a symbiotic framework. 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. Colour names produced by the approach were favoured by human judges to names given by humans 70% of the time.Ī genetic algorithm-based method is elaborated for slogan generation. We show how a metaphor interpretation model can be used in generating metaphors and metaphorical expressions.įurthermore, 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. It obtains the state of the art results and is comparable to the interpretations given by humans. The method does not rely on hand-annotated data and it is purely data-driven. I present a novel method for interpreting one of the most difficult rhetoric devices in the figurative use of language: metaphors. 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. At the same time, research has been conducted in computational aesthetics, which essentially tries to analyse creativity exhibited in art. Computational creativity has received a good amount of research interest in generating creative artefacts programmatically. ![]()
0 Comments
Leave a Reply. |