AI RESEARCH
WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention
arXiv CS.AI
•
ArXi:2603.23319v1 Announce Type: cross Temporal Relation Extraction (TRE) requires identifying how two events or temporal expressions are related in time. Existing attention-based models often highlight globally salient tokens but overlook the pair-specific cues that actually determine the temporal relation. We propose WISTERIA (Weak Implicit Signal-based Temporal Relation Extraction with Attention), a framework that examines whether the top-K attention components conditioned on each event pair truly encode interpretable evidence for temporal classification.