Meanings are like Onions: a Layered Approach to Metaphor Processing

2025-07-14

AI Summary

This study addresses the computational modeling challenge posed by the multi-layered nature of metaphorical meaning. We propose a three-tier hierarchical cognitive model: (1) a content analysis layer that identifies source–target domain mappings; (2) a conceptual blending layer that formalizes cross-domain integration mechanisms; and (3) a pragmatic intent layer—novelly introducing communicative function constraints as a systematic component. Methodologically, we integrate conceptual annotation, dynamic conceptual blending modeling, and pragmatic lexical representation to construct a unified formal framework balancing cognitive plausibility and contextual sensitivity. Key contributions include: (1) the first explicit formalization of pragmatic intent as a core computational layer in metaphor processing; (2) continuous interpretation from surface-level associations to deep pragmatic inference; and (3) an extensible, multi-granular metaphor explanation architecture that significantly enhances semantic representation depth and situational adaptability in NLU systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Analogy
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

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.

Problem

• Modeling metaphor processing as a multi-layered cognitive phenomenon
• Integrating content analysis, conceptual blending, and pragmatic intentionality
• Enabling context-sensitive computational metaphor interpretation

Innovation

• Stratified model for multi-layered metaphor processing
• Combines content analysis, blending, and intentionality
• Unifies layers into a context-sensitive formal framework