Dancing with Deer: A Constructional Perspective on MWEs in the Era of LLMs

2025-08-21

AI Summary

This study addresses the acquisition, generalization, and representation of multiword expressions (MWEs) within a usage-based construction grammar framework, responding to the challenge of modeling linguistic creativity in large language models (LLMs). Method: Integrating construction grammar theory, construction template modeling, the Uniform Meaning Representation framework, and psycholinguistic experiments, the authors propose cross-modal construction templates to unify the representation of polysemous morphosyntactic units. Contribution/Results: Both humans and LLMs exhibit one-shot generalization of novel MWEs; however, only humans perform deep analogical reasoning across multiple new expressions—highlighting the central role of the construction inventory in abstract pattern extraction and creative usage. This work is the first to systematically uncover the cognitive mechanism by which humans leverage embodied experience for constructional generalization. It further provides theoretical constraints and modeling pathways for enhancing LLMs’ capacity to process MWEs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Lexical Semantics and Morphology

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

In this chapter, we argue for the benefits of understanding multiword expressions from the perspective of usage-based, construction grammar approaches. We begin with a historical overview of how construction grammar was developed in order to account for idiomatic expressions using the same grammatical machinery as the non-idiomatic structures of language. We cover a comprehensive description of constructions, which are pairings of meaning with form of any size (morpheme, word, phrase), as well as how constructional approaches treat the acquisition and generalization of constructions. We describe a successful case study leveraging constructional templates for representing multiword expressions in English PropBank. Because constructions can be at any level or unit of form, we then illustrate the benefit of a constructional representation of multi-meaningful morphosyntactic unit constructions in Arapaho, a highly polysynthetic and agglutinating language. We include a second case study leveraging constructional templates for representing these multi-morphemic expressions in Uniform Meaning Representation. Finally, we demonstrate the similarities and differences between a usage-based explanation of a speaker learning a novel multiword expression, such as "dancing with deer," and that of a large language model. We present experiments showing that both models and speakers can generalize the meaning of novel multiword expressions based on a single exposure of usage. However, only speakers can reason over the combination of two such expressions, as this requires comparison of the novel forms to a speaker's lifetime of stored constructional exemplars, which are rich with cross-modal details.

Problem

• Advocating construction grammar for multiword expressions understanding
• Leveraging constructional templates for representing expressions in languages
• Comparing human and LLM generalization of novel multiword expressions

Innovation

• Construction grammar for multiword expressions
• Case studies in English PropBank and Arapaho
• Comparing human and LLM generalization abilities