Temporal Reasoning in AI systems

TL;DR

This paper addresses the challenge of commonsense temporal reasoning in AI by developing knowledge representation and reasoning schemes that improve temporal projection and inference in the Cyc Knowledge Base, enhancing question-answering performance.

Contribution

It introduces a novel approach using discrete survival functions for temporal extrapolation, improving AI systems' ability to reason about fluents over time.

Findings

Significant improvements in Q/A performance using the proposed methods

Effective extrapolation of fluent durations with temporal constraints

Enhanced reasoning capabilities in the Cyc Knowledge Base

Abstract

Commonsense temporal reasoning at scale is a core problem for cognitive systems. The correct inference of the duration for which fluents hold is required by many tasks, including natural language understanding and planning. Many AI systems have limited deductive closure because they cannot extrapolate information correctly regarding existing fluents and events. In this study, we discuss the knowledge representation and reasoning schemes required for robust temporal projection in the Cyc Knowledge Base. We discuss how events can start and end risk periods for fluents. We then use discrete survival functions, which represent knowledge of the persistence of facts, to extrapolate a given fluent. The extrapolated intervals can be truncated by temporal constraints and other types of commonsense knowledge. Finally, we present the results of experiments to demonstrate that these methods obtain significant improvements in terms of Q/A performance.