arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.08991cs.CLcs.LG
收藏

科学即探索:概念隐喻理论的计算前沿

Science is Exploration: Computational Frontiers for Conceptual Metaphor Theory

Cornell University(康奈尔大学);Aarhus University(奥胡斯大学)

Rebecca M. M. Hicke, Ross Deans Kristensen-McLachlan

AI总结:

本文探讨大型语言模型能否准确识别和解释自然语言中的概念隐喻,通过基于隐喻标注指南的新颖提示技术,证明其能有效应用人类标注程序并展现深厚语言学知识,为大规模计算研究提供了有力工具。

摘要:

隐喻无处不在。从最精妙的诗歌到看似枯燥的学术散文,它们广泛存在于自然语言的各个领域。语言认知科学的大量研究主张概念隐喻的存在,即用另一领域的语言对某一经验领域进行系统建构。概念隐喻不仅是修辞手法,更是类比推理在人类认知中发挥作用的关键证据。本文探讨大型语言模型(LLMs)能否准确识别并解释自然语言数据中此类概念隐喻的存在。基于隐喻标注指南,我们采用一种新颖的提示技术,证明 LLMs 是用于概念隐喻大规模计算研究的有前景工具。此外,我们表明 LLMs 能够应用为人类标注员设计的程序性指南,展现出惊人的语言学知识深度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑