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

TL;DR

This paper presents a probabilistic, factorized model for understanding vague temporal adverbials, capturing their semantics as distributions that adapt to different event types, improving interpretability and extendability.

Contribution

Introduces a novel factorized probabilistic model for vague temporal adverbials that outperforms non-factorized models in simplicity and extendability.

Findings

Model fits speaker judgment data effectively.

Factorized model is simpler and more extendable.

Comparable predictive power to non-factorized models.

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.