Temporal Reasoning on Implicit Events from Distant Supervision
This addresses a new challenge in temporal reasoning for NLP systems, moving beyond explicit events to improve understanding of implicit scenarios, though it is incremental in advancing existing methods.
The authors tackled the problem of temporal reasoning on implicit events, which are not explicitly mentioned in text but can be inferred via commonsense, by introducing the TRACIE dataset and proposing SYMTIME, a neuro-symbolic model that outperforms baselines by 5% on TRACIE and up to 11% in zero-shot settings.
We propose TRACIE, a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events -- events that are not mentioned explicitly in natural language text but can be inferred from it. This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events. Human readers can infer implicit events via commonsense reasoning, resulting in a more comprehensive understanding of the situation and, consequently, better reasoning about time. We find, however, that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. To address this, we propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations to infer end times. SYMTIME outperforms strong baseline systems on TRACIE by 5%, and by 11% in a zero prior knowledge training setting. Our approach also generalizes to other temporal reasoning tasks, as evidenced by a gain of 1%-9% on MATRES, an explicit event benchmark.