论文标题
部分可观测时空混沌系统的无模型预测
Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
论文作者
论文摘要
在本文中，我们试图从两个角度提高temprel提取模型的忠诚。第一个观点是根据上下文描述真正提取。为了实现这一目标，我们建议进行反事实分析，以减轻两种重要类型的训练偏见的影响：事件触发偏见和频繁的标签偏见。我们还将时态信息添加到事件表示中，以明确地重点放在上下文描述上。第二个观点是在文本中未描述任何关系时提供适当的不确定性估计，并避免提取。通过在模型预测的分类分布上对Dirichlet的参数化，我们改善了正确性可能性的模型估计值，并使Temprel预测更加选择性。我们还采用温度缩放来重新校准减轻偏置后的模型置信度度量。通过对MATRES，MATRES-DS和TDDISCOURSE的实验分析，我们证明了与SOTA方法相比，我们的模型更忠实地提取了Temprel和时间表，尤其是在分布变化下。
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. To achieve this, we propose to conduct counterfactual analysis to attenuate the effects of two significant types of training biases: the event trigger bias and the frequent label bias. We also add tense information into event representations to explicitly place an emphasis on the contextual description. The second perspective is to provide proper uncertainty estimation and abstain from extraction when no relation is described in the text. By parameterization of Dirichlet Prior over the model-predicted categorical distribution, we improve the model estimates of the correctness likelihood and make TempRel predictions more selective. We also employ temperature scaling to recalibrate the model confidence measure after bias mitigation. Through experimental analysis on MATRES, MATRES-DS, and TDDiscourse, we demonstrate that our model extracts TempRel and timelines more faithfully compared to SOTA methods, especially under distribution shifts.
