Abstract
Existing models to extract temporal relations between events lack a principled method to incorporate external knowledge. In this study, we introduce Bayesian-Trans, a Bayesian learning-based method that models the temporal relation representations as latent variables and infers their values via Bayesian inference and translational functions. Compared to conventional neural approaches, instead of performing point estimation to find the best set parameters, the proposed model infers the parameters' posterior distribution directly, enhancing the model's capability to encode and express uncertainty about the predictions. Experimental results on the three widely used datasets show that Bayesian-Trans outperforms existing approaches for event temporal relation extraction. We additionally present detailed analyses on uncertainty quantification, comparison of priors, and ablation studies, illustrating the benefits of the proposed approach.
Abstract (translated)
现有的模型用于提取事件之间的时间关系缺乏一种原则性的方法,以整合外部知识。在本研究中,我们介绍了贝叶斯转换(Bayesian-Trans),一种基于贝叶斯学习的模型,将时间关系表示为隐变量,并通过贝叶斯推理和翻译函数推断其值。与传统的神经网络方法相比, proposed 模型不再进行点估计,而是直接推断参数的后验分布,增强了模型对预测的不确定性编码和表达能力。对三个广泛应用的数据集的实验结果表明,贝叶斯转换在事件时间关系提取方面比现有方法更有效。我们还提供了对不确定性量化、比较先前知识和烧灼研究等方面的详细分析,以说明该方法的优势。
URL
https://arxiv.org/abs/2302.04985