MetFuse: Figurative Fusion between Metonymy and Metaphor
TLDR
MetFuse introduces the first dataset for figurative fusion of metonymy and metaphor, improving classification and showing how these figures interact.
Key contributions
- Introduces a framework to generate metonymic, metaphoric, and hybrid figurative sentences.
- Presents MetFuse, the first dataset (4,000 sentences) for metonymy-metaphor fusion.
- Shows MetFuse improves metonymy and metaphor classification, with hybrid examples yielding largest gains.
- Reveals that metaphor presence makes metonymy more explicit for human annotators and LLMs.
Why it matters
This paper addresses a critical gap in NLP by studying metonymy and metaphor's co-occurrence, rather than in isolation. The MetFuse dataset and findings offer a new resource and insights into how these figures interact, potentially leading to more nuanced language understanding in AI systems.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.