本文转载自公众号：图谱学苑 。

在面向文本数据构建知识图谱的过程中，一项十分重要的任务是进行三元组的规范化，即把不同三元组中实际指向同一个实体的主体（subject）或客体（object）链接到一起；类似的，对于不同三元组中的谓词或属性若是同样的意思，则也需要进行标准化。一个常用的方法是把这些三元组聚类，聚类的过程可以采用人工定义的特征，也可以基于所学到的分布式表示。然而传统的聚类大多采用的是层次聚类，时间复杂度较高，并且很多新出现的实体难以链接到已有的知识图谱中，为了解决这一问题，ICDE 2019有研究人员提出了一个解决方案【12】，作者们提出了一种同时考虑实体和关系标准化的联合策略，并且引入了领域知识。

[1] Efficient Knowledge Graph Accuracy Evaluation, VLDB 2019

[2] An Efficient Parallel Keyword Search Engine on Knowledge Graphs, ICDE 2019

[3] CATAPULT Data-driven Selection of Canned Patterns for Efficient Visual Graph Query Formulation, SIGMOD 2019

[4] Interactive Graph Search, SIGMOD 2019

[5] Answering Why-questions by Exemplars in Attributed Graphs, SIGMOD 2019

[6] Experimental Analysis of Streaming Algorithms for Graph Partitioning, SIGMOD 2019

[7] Unboundedness and Efficiency of Truss Maintenance in Evolving Graphs, SIGMOD 2019

[8] Constrained Shortest Path in a Time-Dependent Graph, VLDB 2019

[9] NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding, ICDE 2019

[10] 2ED: An Efficient Entity Extraction Algorithm using Two-Level Edit-Distance, ICDE 2019

[11] Building a Broad Knowledge Graph for Products, ICDE 2019

[12] Canonicalization of Open Knowledge Bases with Side Information from the Source Text, ICDE 2019

[13] Time Constrained Continuous Subgraph Search over Streaming Graphs, ICDE 2019

[14] TurboFlux: A Fast Continuous Subgraph Matching System for Streaming Graph Data, SIGMOD 2018

[15] Robust Discovery of Positive and Negative Rules in Knowledge-Bases, ICDE 2018

[16] Query-Driven On-The-Fly Knowledge Base Construction, VLDB 2018

[17] Question Answering Over Knowledge Graphs: Question Understanding Via Template Decomposition，VLDB 2018

[18] Interactive Graph Search, SIGMOD 2019

[19] Answering Why-questions by Exemplars in Attributed Graphs, SIGMOD 2019

[20] Experimental Analysis of Streaming Algorithms for Graph Partitioning, SIGMOD 2019

OpenKG

开放知识图谱（简称 OpenKG）旨在促进中文知识图谱数据的开放与互联，促进知识图谱和语义技术的普及和广泛应用。

点击阅读原文，进入 OpenKG 博客。