MetFuse: Figurative Fusion between Metonymy and Metaphor

TL;DR

This paper introduces MetFuse, a dataset and framework for studying the fusion of metonymy and metaphor in language, demonstrating improved classification and insights into their interaction.

Contribution

It presents the first dataset of figurative fusion between metonymy and metaphor, along with a framework for generating and analyzing such cases.

Findings

Augmenting training data with MetFuse improves figurative language classification.

Hybrid examples yield the largest gains on metonymy tasks.

Presence of metaphor enhances metonymy detection in hybrid sentences.

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.