Introduction
知识图谱（Knowledge Graph），在图书情报界称为知识域可视化或知识领域映射地图，是显示知识发展进程与结构关系的一系列各种不同的图形，用可视化技术描述知识资源及其载体，挖掘、分析、构建、绘制和显示知识及它们之间的相互联系。
A KG is a multi-relational graph composed of entities (nodes) and relations (different types of edges). Each edge is represented as a triple of the form (head entity, relation, tail entity), also called a fact, indicating that two entities are connected by a specific relation, e.g., (AlfredHitchcock, DirectorOf, Psycho). Although effective in representing structured data, the underlying symbolic nature of such triples usually makes KGs hard to manipulate.
To tackle this issue, a new research direction known as knowledge graph embedding has been proposed and quickly gained massive attention.
Knowledge graph (KG) embedding is to embed components of a KG including entites and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. Those entity and relation embeddings can further be used to benefit all kinds of tasks, such as KG completion, relation extraction, entity classification, and entity resolution.
technique
A typical KG embedding technique generally consists of three steps:
- representing entities and relations,
- defining a scoring function, and
- learning entity and relation representations.
We roughly categorize such embedding techniques into two groups: translational distance models and semantic matching models. The former use distance-based scoring functions, and the latter similarity-based ones.
Translational Distance Models
Translational distance models exploit distance-based scoring functions. They measure the plausibility of a fact as the distance between the two entities, usually after a translation carried out by the relation.
TransE and Its Extensions
Despite its simplicity and efficiency, TransE has flaws in dealing with 1-to-N, N-to-1, and N-to-N relations.
To overcome the disadvantages of TransE in dealing with 1-to-N, N-to-1, and N-to-N relations, an effective strategy is to allow an entity to have distinct representations when involved in different relations.
TransH
TransH follows this general idea, by introducing relation-specific hyperplanes.
Knowledge Graph Embedding: A Survey of Approaches and Applications
Quan Wang , Zhendong Mao , Bin Wang, and Li Guo