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. Unlike prior works assuming explicit markers such as before, after, or when, WISTERIA considers signals as any lexical, syntactic, or morphological element implicitly expressing temporal order. By combining multi-head attention with pair-conditioned top-K pooling, the model isolates the most informative contextual tokens for each pair. We conduct extensive experiments on TimeBank-Dense, MATRES, TDDMan, and TDDAuto, including linguistic analyses of top-K tokens. Results show that WISTERIA achieves competitive accuracy and reveals pair-level rationales aligned with temporal linguistic cues, offering a localized and interpretable view of temporal reasoning.

翻译：时间关系抽取（Temporal Relation Extraction, TRE）要求识别两个事件或时间表达式在时间上的关联方式。现有的基于注意力机制的模型通常关注全局显著词元，却忽略了实际决定时间关系的配对特定线索。本文提出WISTERIA（基于弱隐信号的注意力机制时间关系抽取），该框架检验每个事件对上的前K个注意力分量是否真正编码了可用于时间分类的可解释证据。与以往假设存在"之前"、"之后"、"当……时"等显式标记的工作不同，WISTERIA将信号视为任何隐式表达时间顺序的词汇、句法或形态成分。通过将多头注意力与基于事件对的条件化前K池化相结合，模型能够为每个事件对分离出最具信息量的上下文词元。我们在TimeBank-Dense、MATRES、TDDMan和TDDAuto上开展了广泛实验，包括对前K个词元的语言学分析。结果表明，WISTERIA在取得有竞争力精度的同时，能揭示与时间语言线索相一致的配对层面解释，从而为时间推理提供局部化且可解释的视角。