当前位置: X-MOL 学术arXiv.cs.CL › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
arXiv - CS - Computation and Language Pub Date : 2020-06-29 , DOI: arxiv-2006.16365
Hung Nghiep Tran and Atsuhiro Takasu

Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between these whole embeddings, potentially making the model excessively expensive or requiring specially designed interaction mechanisms. In this work, we propose the multi-partition embedding interaction (MEI) model with block term format to systematically address this problem. MEI divides each embedding into a multi-partition vector to efficiently restrict the interactions. Each local interaction is modeled with the Tucker tensor format and the full interaction is modeled with the block term tensor format, enabling MEI to control the trade-off between expressiveness and computational cost, learn the interaction mechanisms from data automatically, and achieve state-of-the-art performance on the link prediction task. In addition, we theoretically study the parameter efficiency problem and derive a simple empirically verified criterion for optimal parameter trade-off. We also apply the framework of MEI to provide a new generalized explanation for several specially designed interaction mechanisms in previous models.

中文翻译:

用于知识图完成的块术语格式的多分区嵌入交互

知识图完成是一项重要任务,旨在预测实体之间缺失的关系链接。知识图嵌入方法通过将实体和关系表示为嵌入向量并对它们的交互进行建模以计算每个三元组的匹配分数来执行此任务。以前的工作通常将每个嵌入视为一个整体,并对这些整个嵌入之间的交互进行建模,这可能会使模型过于昂贵或需要专门设计的交互机制。在这项工作中,我们提出了具有块术语格式的多分区嵌入交互(MEI)模型来系统地解决这个问题。MEI 将每个嵌入划分为一个多分区向量,以有效地限制交互。每个局部交互都用 Tucker 张量格式建模,完整的交互用块项张量格式建模,使 MEI 能够控制表达能力和计算成本之间的权衡,自动从数据中学习交互机制,并实现 state-of - 在链接预测任务上的最佳表现。此外,我们从理论上研究了参数效率问题,并推导出了一个简单的、经过经验验证的最佳参数权衡标准。我们还应用 MEI 的框架为先前模型中的几种专门设计的交互机制提供了新的广义解释。并在链接预测任务上实现最先进的性能。此外,我们从理论上研究了参数效率问题,并推导出了一个简单的、经过经验验证的最佳参数权衡标准。我们还应用 MEI 的框架为先前模型中的几种专门设计的交互机制提供了新的广义解释。并在链接预测任务上实现最先进的性能。此外,我们从理论上研究了参数效率问题,并推导出了一个简单的、经过经验验证的最佳参数权衡标准。我们还应用 MEI 的框架为先前模型中的几种专门设计的交互机制提供了新的广义解释。
更新日期:2020-07-01
down
wechat
bug