# Meanings are like Onions: a Layered Approach to Metaphor Processing

arXiv: https://arxiv.org/abs/2507.10354 · HTML: https://mlsanity.com/paper/2507.10354/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models](https://mlsanity.com/paper/2406.02061/) (2024)
- [MetaCLUE: Towards Comprehensive Visual Metaphors Research](https://mlsanity.com/paper/2212.09898/) (2022)
- [ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models](https://mlsanity.com/paper/2305.05050/) (2023)
- [Amnestic Forgery: an Ontology of Conceptual Metaphors](https://mlsanity.com/paper/1805.12115/) (2018)
- [Science is Exploration: Computational Frontiers for Conceptual Metaphor Theory](https://mlsanity.com/paper/2410.08991/) (2024)
- [Logic Augmented Generation](https://mlsanity.com/paper/2411.14012/) (2024)
- [A framework for annotating and modelling intentions behind metaphor use](https://mlsanity.com/paper/2407.03952/) (2024)
- [EFO: the Emotion Frame Ontology](https://mlsanity.com/paper/2401.10751/) (2024)
- [Enhancing multimodal analogical reasoning with Logic Augmented Generation](https://mlsanity.com/paper/2504.11190/) (2025)

## Built on by (most cited first, 1 of 1)

- [Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models](https://mlsanity.com/paper/2609.02502/) (2026)

## Abstract (arXiv)

Metaphorical meaning is not a flat mapping between concepts, but a complex cognitive phenomenon that integrates multiple levels of interpretation. In this paper, we propose a stratified model of metaphor processing that treats meaning as an onion: a multi-layered structure comprising (1) content analysis, (2) conceptual blending, and (3) pragmatic intentionality. This three-dimensional framework allows for a richer and more cognitively grounded approach to metaphor interpretation in computational systems. At the first level, metaphors are annotated through basic conceptual elements. At the second level, we model conceptual combinations, linking components to emergent meanings. Finally, at the third level, we introduce a pragmatic vocabulary to capture speaker intent, communicative function, and contextual effects, aligning metaphor understanding with pragmatic theories. By unifying these layers into a single formal framework, our model lays the groundwork for computational methods capable of representing metaphorical meaning beyond surface associations, toward deeper, more context-sensitive reasoning.