A Factorized Probabilistic Model of the Semantics of Vague Temporal Adverbials Relative to Different Event Types

2025-05-02

AI Summary

This paper addresses the challenge of modeling fuzzy temporal adverbs (e.g., “recently”, “just”), whose semantics vary across event types and lack explicit temporal grounding. We propose a factorized probabilistic model that decouples adverb semantics into two components: a universal distribution capturing cross-event regularities, and an event-specific distribution encoding type-dependent temporal biases; these are combined multiplicatively to yield context-aware temporal distance estimates. To our knowledge, this is the first approach to incorporate Occam’s razor into fuzzy temporal semantics modeling—explicitly favoring parsimonious, interpretable, and generalizable representations. Experiments show that our method matches the predictive accuracy of non-factorized single-Gaussian baselines while reducing parameter count significantly, demonstrating superior efficiency and scalability across diverse event types.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Vague temporal adverbials, such as recently, just, and a long time ago, describe the temporal distance between a past event and the utterance time but leave the exact duration underspecified. In this paper, we introduce a factorized model that captures the semantics of these adverbials as probabilistic distributions. These distributions are composed with event-specific distributions to yield a contextualized meaning for an adverbial applied to a specific event. We fit the model's parameters using existing data capturing judgments of native speakers regarding the applicability of these vague temporal adverbials to events that took place a given time ago. Comparing our approach to a non-factorized model based on a single Gaussian distribution for each pair of event and temporal adverbial, we find that while both models have similar predictive power, our model is preferable in terms of Occam's razor, as it is simpler and has better extendability.

Problem

• Modeling probabilistic semantics of vague temporal adverbials
• Capturing event-specific contextualized meanings of adverbials
• Comparing factorized vs. non-factorized models for temporal interpretation

Innovation

• Factorized model captures vague adverbials probabilistically
• Composes event-specific distributions for contextualized meaning
• Simpler and more extendable than non-factorized approach