Title :
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
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;
Conference_Titel :
Technologies and Applications of Artificial Intelligence (TAAI), 2013 Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4799-2528-5
DOI :
10.1109/TAAI.2013.32
