arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.04828cs.AIcs.IR
收藏

基于多任务神经网络的知识图谱非离散属性预测

Multi-task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs

Nanyang Technological University(南洋理工大学);Institute for Infocomm Research(信息通信研究所)

Yi Tay, Luu Anh Tuan, Minh C. Phan, Siu Cheung Hui

摘要:

许多流行的知识图谱(如Freebase、YAGO或DBPedia)为每个实体维护一个非离散属性列表。直观地说,这些属性,如高度,价格或人口计数能够丰富的特点,实体在知识图谱。这种额外的信息源可以帮助缓解知识图谱中普遍存在的固有稀疏性和不完整性问题。不幸的是,由于在固有二进制性质的知识图谱中处理非离散数据类型的挑战性本质,许多最先进的关系学习模型忽略了该信息。在本文中,我们提出了一种新的多任务神经网络方法的编码和预测的非离散属性信息的关系设置。具体来说,我们训练一个用于三重预测的神经网络,以及一个用于属性值回归的单独网络。通过多任务学习,我们能够学习实体,关系和属性的表示,这些表示编码了关于两个任务的信息。此外,这些属性不仅作为信息源而且作为预测目标对于许多预测任务是中心的。因此,能够在关系学习环境中编码、合并和预测这些信息的模型也非常有吸引力。我们表明,我们的方法优于许多国家的最先进的方法的任务,关系三元组分类和属性值预测。

英文摘要:

Many popular knowledge graphs such as Freebase, YAGO or DBPedia maintain a list of non-discrete attributes for each entity. Intuitively, these attributes such as height, price or population count are able to richly characterize entities in knowledge graphs. This additional source of information may help to alleviate the inherent sparsity and incompleteness problem that are prevalent in knowledge graphs. Unfortunately, many state-of-the-art relational learning models ignore this information due to the challenging nature of dealing with non-discrete data types in the inherently binary-natured knowledge graphs. In this paper, we propose a novel multi-task neural network approach for both encoding and prediction of non-discrete attribute information in a relational setting. Specifically, we train a neural network for triplet prediction along with a separate network for attribute value regression. Via multi-task learning, we are able to learn representations of entities, relations and attributes that encode information about both tasks. Moreover, such attributes are not only central to many predictive tasks as an information source but also as a prediction target. Therefore, models that are able to encode, incorporate and predict such information in a relational learning context are highly attractive as well. We show that our approach outperforms many state-of-the-art methods for the tasks of relational triplet classification and attribute value prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑