Science is Exploration: Computational Frontiers for Conceptual Metaphor Theory

TL;DR

This paper investigates the capability of Large Language Models to identify and explain conceptual metaphors in natural language, demonstrating their potential as tools for large-scale computational metaphor research.

Contribution

It introduces a novel prompting technique for LLMs to annotate metaphors and shows their effectiveness in understanding complex linguistic concepts.

Findings

LLMs can accurately identify conceptual metaphors in text.

LLMs apply procedural guidelines similar to human annotators.

LLMs display deep linguistic knowledge in metaphor analysis.

Abstract

Metaphors are everywhere. They appear extensively across all domains of natural language, from the most sophisticated poetry to seemingly dry academic prose. A significant body of research in the cognitive science of language argues for the existence of conceptual metaphors, the systematic structuring of one domain of experience in the language of another. Conceptual metaphors are not simply rhetorical flourishes but are crucial evidence of the role of analogical reasoning in human cognition. In this paper, we ask whether Large Language Models (LLMs) can accurately identify and explain the presence of such conceptual metaphors in natural language data. Using a novel prompting technique based on metaphor annotation guidelines, we demonstrate that LLMs are a promising tool for large-scale computational research on conceptual metaphors. Further, we show that LLMs are able to apply procedural guidelines designed for human annotators, displaying a surprising depth of linguistic knowledge.