Interpretable dimensions support an effect of agentivity and telicity on split intransitivity

2025-11-20

AI Summary

Traditional semantic rating tasks inadequately capture deep, continuous semantic properties—particularly agentivity and telicity—that are hypothesized to underlie the syntactic split of intransitive verbs (i.e., unaccusative vs. unergative classification). Method: To address this limitation, we propose a seed-word-based, interpretable method for constructing semantic dimensions, integrating human judgments with computational models (e.g., distributional word vector space projections) to quantify verbs’ continuous positioning along agentivity and telicity scales. Contribution/Results: Empirical analysis demonstrates that both dimensions significantly predict syntactic behavior, providing a robust semantic account of intransitive verb splitting. The approach enhances transparency and reproducibility in semantic property modeling and offers a novel interface between formal syntax and cognitive semantics.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Intransitive verbs fall into two different syntactic classes, unergatives and unaccusatives. It has long been argued that verbs describing an agentive action are more likely to appear in an unergative syntax, and those describing a telic event to appear in an unaccusative syntax. However, recent work by Kim et al. (2024) found that human ratings for agentivity and telicity were a poor predictor of the syntactic behavior of intransitives. Here we revisit this question using interpretable dimensions, computed from seed words on opposite poles of the agentive and telic scales. Our findings support the link between unergativity/unaccusativity and agentivity/telicity, and demonstrate that using interpretable dimensions in conjunction with human judgments can offer valuable evidence for semantic properties that are not easily evaluated in rating tasks.

Problem

• Investigating the relationship between agentivity/telicity and intransitive verb syntax classification
• Evaluating human ratings versus interpretable dimensions for predicting syntactic behavior
• Demonstrating how interpretable dimensions complement human judgments in semantic analysis

Innovation

• Uses interpretable dimensions from seed words
• Links agentivity and telicity to syntactic behavior
• Combines computational methods with human judgments