Skip to content
Open access

The Structural Sources of Verb Meanings Revisited: Large Language Models Display Syntactic Bootstrapping

Sep 2026 · Open Mind · 0 citations

TL;DR

The results show that models’ verb representations degrade more when the authors perturb word order, which removes syntactic information, than when they perturb co-occurrence among content words, which removes semantic information.

Abstract

Syntactic bootstrapping (Gleitman, 1990) is the hypothesis that children use the syntactic environments in which a verb occurs to learn its meaning. Existing evidence for this hypothesis generally involves controlled experimental settings (e.g., Jin & Fisher, 2014; Naigles, 1990; Yuan et al., 2012). In this paper, we leverage the powerful statistical learning abilities of neural language models to examine the contribution of different kinds of cues for word learning when a learner is presented with a corpus of English linguistic input on the scale of a child’s experience. We do this by training two standard types of neural networks (masked and autoregressive transformers) on perturbed datasets where different sources of information relevant to word learning are individually removed. Our results show that models’ verb representations degrade more when we perturb word order, which removes syntactic information, than when we perturb co-occurrence among content words, which removes semantic information. Furthermore, the representations of mental verbs, for which syntactic bootstrapping has been shown to be particularly crucial in human verb learning, are more negatively impacted in the training regime with perturbed word order as compared to physical verbs. In contrast, while word order also affects models’ representations of nouns, the nouns are influenced more by co-occurrence information than the verbs are. In addition to reinforcing the important role of syntactic bootstrapping in verb learning, our results demonstrate the viability of testing developmental hypotheses on a large scale through manipulating the learning environments of large language models.

Read PDF

Similar papers

#natural language process... Preprint Sep 2026

Modeling the Developmental Shift in Telicity Acquisition

Acquiring telicity, which is the distinction between bounded (e.g., ate an apple) and unbounded (e.g., ate apples) events, requires first language (L1) learners to map surface-level and semantic cues to abstract event structures, but the computational trajectory of this mapping is not well understood. We introduce a Di...

Ellie Xia, Parisa Kordjamshidi, Alan Hezao Ke · 0 citations
Open access 2026

Byte-pair Encoding Captures Aspects of Word Meaning that Distributional Semantics Overlooks

Large language models learn word meanings through distributional semantics (i.e., patterns in text), and distribution does not always capture information about taxonomy and function, which are essential to human representations of word meaning. However, sound and spelling often conveys such information, and language...

David A. Haslett, Antoni B. Chan, J. Hsiao · 0 citations
Open access Oct 2026

Constructions with crossed syntactic dependencies show elevated lexical cohesion: the compensatory collocation hypothesis

Abstract Natural languages avoid syntactic structures with crossed syntactic dependencies. To the extent that such structures nonetheless occur, they have been explained as the result of competing motivations, such as dependency length minimization, the facilitation of incremental language processing, or the preservati...

Martin Hilpert · 0 citations

Linguistic Features for Interpretable Textual Entailment

SLITE is presented, an explainable hybrid model for Recognizing Textual Entailment that integrates two complementary layers of semantic analysis: a structural-relational layer, based on semantic compatibility and incompatibility between compositional entities, and a distributional-informational layer, based on structur...

David Torres-Moreno, J. Hermosillo-Valadez, Asela Reig-Alamillo · 0 citations

A LSTM language model learns Hindi-Urdu case-agreement interactions, and has a linear encoding of case

A two-layer LSTM language model trained on 250M morphemes of Hindi data can capture the relatively complex interaction between case and agreement in Hindi-Urdu, and it is shown that this model encodes case-marking linearly, implementing a geometrically intuitive and inter-pretable syntactic processing mechanism.

Satoru Ozaki, Rajesh Bhatt, Brian Dillon · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.