arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.06910cs.CLcs.IRcs.LG
收藏

基于CNN的知识图谱学习双链模型

CNN-based Dual-Chain Models for Knowledge Graph Learning

The Ohio State University(俄亥俄州立大学);NEC Laboratories America, Inc(NEC美国研究院)

Bo Peng, Renqiang Min, Xia Ning

摘要:

知识图谱学习在实际应用中部署机器学习和数据采掘模型时,在集成特定领域的知识库方面起着至关重要的作用。现有的知识图谱学习方法主要集中在将实体间的关系建模为实体间的转换,当新的实体出现时,这些方法中的许多方法都不能处理zero-shot问题。本文提出了一种新的基于卷积神经网络(CNN)的双链模型。与基于翻译的方法不同,在我们的模型中,通过CNN直接捕获关系和实体之间的交互。此外,还同时进行二级学习链,以纳入更多信息,提高业绩。我们还提出了这个模型的扩展,它结合了实体的描述,并从描述中学习第二组实体嵌入。结果表明,扩展模型能够有效地处理zero-shot问题。我们进行了全面的实验,比较我们的方法与15个方法在8个基准数据集。大量的实验结果表明,我们提出的方法达到或优于国家的最先进的知识图谱学习的结果,并优于其他方法的zero-shot问题。此外,我们的方法应用于现实世界的生物医学数据能够产生符合专家领域知识的结果。

英文摘要:

Knowledge graph learning plays a critical role in integrating domain specific knowledge bases when deploying machine learning and data mining models in practice. Existing methods on knowledge graph learning primarily focus on modeling the relations among entities as translations among the relations and entities, and many of these methods are not able to handle zero-shot problems, when new entities emerge. In this paper, we present a new convolutional neural network (CNN)-based dual-chain model. Different from translation based methods, in our model, interactions among relations and entities are directly captured via CNN over their embeddings. Moreover, a secondary chain of learning is conducted simultaneously to incorporate additional information and to enable better performance. We also present an extension of this model, which incorporates descriptions of entities and learns a second set of entity embeddings from the descriptions. As a result, the extended model is able to effectively handle zero-shot problems. We conducted comprehensive experiments, comparing our methods with 15 methods on 8 benchmark datasets. Extensive experimental results demonstrate that our proposed methods achieve or outperform the state-of-the-art results on knowledge graph learning, and outperform other methods on zero-shot problems. In addition, our methods applied to real-world biomedical data are able to produce results that conform to expert domain knowledge.

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。

↑