MetFuse: Figurative Fusion between Metonymy and Metaphor

2026-04-14

AI Summary

This study addresses the frequent co-occurrence of metonymy and metaphor in natural language, a phenomenon long overlooked in computational research that has traditionally treated the two tropes in isolation, lacking systematic modeling and empirical support. To bridge this gap, the work proposes the first generation framework specifically designed for metonymy-metaphor fusion and introduces MetFuse, a high-quality, human-validated dataset comprising 4,000 aligned quadruplets. Evaluations across eight benchmark tasks demonstrate the dataset’s effectiveness: hybrid rhetorical instances significantly enhance metonymy identification performance and reveal that the presence of metaphor increases the detectability of metonymy—both for humans and computational models—thereby providing the first cognitive and computational evidence of interactive effects between these two figurative language phenomena.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Analogy
• Computer Vision: Language and Vision

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Metonymy and metaphor often co-occur in natural language, yet computational work has studied them largely in isolation. We introduce a framework that transforms a literal sentence into three figurative variants: metonymic, metaphoric, and hybrid. Using this framework, we construct MetFuse, the first dedicated dataset of figurative fusion between metonymy and metaphor, containing 1,000 human-verified meaning-aligned quadruplets totaling 4,000 sentences. Extrinsic experiments on eight existing benchmarks show that augmenting training data with MetFuse consistently improves both metonymy and metaphor classification, with hybrid examples yielding the largest gains on metonymy tasks. Using this dataset, we also analyze how the presence of one figurative type impacts another. Our findings show that both human annotators and large language models better identify metonymy in hybrid sentences than in metonymy-only sentences, demonstrating that the presence of a metaphor makes a metonymic noun more explicit. Our dataset is publicly available at: https://github.com/cincynlp/MetFuse.

Problem

• metonymy
• metaphor
• figurative language
• natural language processing

Innovation

• metonymy
• metaphor
• figurative fusion
• dataset construction
• hybrid figurative language