Gen-Meta: Generating Metaphors Using a Combination of AI Reasoning and Corpus-Based Modeling of Formulaic Expressions

Author

Gargett, Andrew ; Barnden, John

Author_Institution

Sch. of Comput. Sci., Univ. of Birmingham, Birmingham, UK

fYear

2013

Firstpage

103

Lastpage

108

Abstract

Metaphor is important in all sorts of mundane discourse [19], [7]: ordinary conversation, news articles, popular novels, advertisements, etc. This presents a challenge to how Artificial Intelligence (AI) systems understand inter-human discourse (e.g. newspaper articles), or produce more natural-seeming language, as most AI research on metaphor has been about its understanding rather than its generation. To redress the balance towards generation of metaphor, we directly tackle the role of AI systems in communication, uniquely combining this with corpus-based results to guide output to more natural forms of expression.

Keywords

inference mechanisms; natural language processing; AI reasoning; Gen-Meta; advertisements; artificial intelligence; corpus-based modeling; corpus-based results; formulaic expressions; interhuman discourse; metaphor generation; mundane discourse; natural-seeming language; news articles; novels; ordinary conversation; Artificial intelligence; Cognition; Diabetes; Educational institutions; Electrocardiography; Natural languages; Pragmatics; Artificial intelligence; Cognitive science; Interactive system; Natural language processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Technologies and Applications of Artificial Intelligence (TAAI), 2013 Conference on

Conference_Location

Taipei

Print_ISBN

978-1-4799-2528-5

Type

conf

DOI

10.1109/TAAI.2013.32

Filename

6783851