Event Temporal Relation Extraction with Bayesian Translational Model
Event Temporal Relation Extraction with Bayesian Translational Model
复制标题
DOI：
10.48550/arxiv.2302.04985
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Xingwei Tan;Gabriele Pergola;Yulan He
中科院分区：
文献类型：
--
作者：
Xingwei Tan;Gabriele Pergola;Yulan He
在事件之间提取临时关系的现有模型缺乏将外部知识纳入外部知识的主要方法。与传统的神经方法相比，推理和翻译功能，而不是执行最佳套装参数参数的后验分布直接增强了模型的编码能力，并在三个广泛使用的数据集中表达了预测结果。 ，先验和消融研究的比较，说明了拟议方法的好处。
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.