One-Class Order Embedding for Dependency Relation Prediction
One-Class Order Embedding for Dependency Relation Prediction
复制标题
DOI：
10.1145/3331184.3331249
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Meng-Fen Chiang;Ee-Peng Lim;Wang-Chien Lee;Xavier Jayaraj Siddarth Ashok;P. K. Prasetyo
中科院分区：
文献类型：
--
作者：
Meng-Fen Chiang;Ee-Peng Lim;Wang-Chien Lee;Xavier Jayaraj Siddarth Ashok;P. K. Prasetyo
通过将实体映射到某个有序嵌入空间来学习实体之间的依赖关系以及这些关系形成的层次结构，可以有效地实现几个重要的应用，包括知识库完成和先决条件关系预测。然而，由于观测数据中存在偏序和缺失关系，学习一个好的顺序嵌入是非常具有挑战性的。此外，大多数应用场景不提供非平凡的负依赖关系实例。因此，我们提出了一个框架，通过探索丰富的语义和层次结构信息的数据进行依赖关系预测。特别是，我们提出了几个负采样策略的基础上，特定的图的中心性属性，补充适当的负样本的正依赖关系，以有效地学习顺序嵌入。这项研究不仅解决了自动恢复缺失的依赖关系的需求，而且还使用几个真实世界的数据集，如涉及课程先决条件关系的课程依赖层次结构，组织中的工作层次结构和论文引用层次结构，解开实体之间的依赖关系。在合成和真实世界的数据集上进行了大量的实验，以证明预测的准确性，并使用学习的顺序嵌入来获得见解。
Learning the dependency relations among entities and the hierarchy formed by these relations by mapping entities into some order embedding space can effectively enable several important applications, including knowledge base completion and prerequisite relations prediction. Nevertheless, it is very challenging to learn a good order embedding due to the existence of partial ordering and missing relations in the observed data. Moreover, most application scenarios do not provide non-trivial negative dependency relation instances. We therefore propose a framework that performs dependency relation prediction by exploring both rich semantic and hierarchical structure information in the data. In particular, we propose several negative sampling strategies based on graph-specific centrality properties, which supplement the positive dependency relations with appropriate negative samples to effectively learn order embeddings. This research not only addresses the needs of automatically recovering missing dependency relations, but also unravels dependencies among entities using several real-world datasets, such as course dependency hierarchy involving course prerequisite relations, job hierarchy in organizations, and paper citation hierarchy. Extensive experiments are conducted on both synthetic and real-world datasets to demonstrate the prediction accuracy as well as to gain insights using the learned order embedding.