知识图谱概览：表示、获取和应用.pdf

AllenLV

117

25页

1次

2023-11-19

免费下载

A Survey on Knowledge Graphs:

Representation, Acquisition and Applications

Shaoxiong Ji, Shirui Pan, Erik Cambria, Senior Member, IEEE,

Pekka Marttinen, Philip S. Yu, Fellow, IEEE,

Abstract—Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations

between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey,

we provide a comprehensive review on knowledge graph covering overall research topics about 1) knowledge graph representation

learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize

recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies

on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models

and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference and

logical rule reasoning are reviewed. We further explore several emerging topics including meta relational learning, commonsense

reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of

datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

Index Terms—Knowledge graph, representation lear ning, knowledge graph completion, relation extraction, reasoning.

1 INTRODUCTION

NCORPORATING human knowledge is one of the research

directions of artiﬁcial intelligence (AI). Knowledge rep-

resentation and reasoning, inspired by human’s problem

solving, is to represent knowledge for intelligent systems to

gain the ability to solve complex tasks. Recently, knowledge

graphs as a form of structured human knowledge have

drawn great research attention from both the academia and

the industry. A knowledge graph is a structured representa-

tion of facts, consisting of entities, relationships and semantic

descriptions. Entities can be real-world objects and abstract

concepts, relationships represent the relation between entities,

and semantic descriptions of entities and their relationships

contain types and properties with a well-deﬁned meaning.

Property graphs or attributed graphs are widely used, in

which nodes and relations have properties or attributes.

The term of knowledge graph is synonymous with

knowledge base with a minor difference. A knowledge

graph can be viewed as a graph when considering its

graph structure. When it involves formal semantics, it

can be taken as a knowledge base for interpretation

and inference over facts. Examples of knowledge base

and knowledge graph are illustrated in Fig. 1. Knowl-

edge can be expressed in a factual triple in the form of

(head, relation, tail)

(subject, predicate, object)

under

•

S. Ji is with Aalto University, Finland and The University of Queensland,

Australia. E-mail: shaoxiong.ji@aalto.ﬁ

•

S. Pan is with Monash University, Australia. E-

mail: shirui.pan@monash.edu

•

E. Cambria is with Nanyang Technological University, Singapore. E-

mail: cambria@ntu.edu.sg

•

P. Marttinen is with Aalto University, Finland. E-

mail: pekka.marttinen@aalto.ﬁ

•

P. S. Yu is with University of Illinois at Chicago, USA. E-

mail: psyu@uic.edu

• S. Pan is the corresponding author.

the resource description framework (RDF), for example,

(Albert Einstein, WinnerOf, Nobel Prize)

. It can also be repre-

sented as a directed graph with nodes as entities and edges as

relations. For simplicity and following the trend of research

community, this paper uses the terms knowledge graph and

knowledge base interchangeably.

(Albert Einstein, BornIn, German Empire)

(Albert Einstein, SonOf, Hermann Einstein)

(Albert Einstein, GraduateFrom, University of Zurich)

(Albert Einstein, WinnerOf, Nobel Prize in Physics)

(Albert Einstein, ExpertIn, Physics)

(Nobel Prize in Physics, AwardIn, Physics)

(The theory of relativity, TheoryOf, Physics)

(Albert Einstein, SupervisedBy, Alfred Kleiner)

(Alfred Kleiner, ProfessorOf, University of Zurich)

(The theory of relativity, ProposedBy, Albert Einstein)

(Hans Albert Einstein, SonOf, Albert Einstein)

(a) Factual triples in knowl-

edge base

Albert

Einstein

Nobel Prize

in Physics

German

Empire

The theory

of relativity

Hans Albert

Einstein

Physics

Alfred

Kleiner

Hermann

Einstein

University

of Zurich

AwardIn

SonOf

ProposedBy

TheoryOf

ExpertIn

WinnerOf

SupervisedBy

ProfessorOf

GraduateFrom

BornIn

(b) Entities and relations in

knowledge graph

Fig. 1: An example of knowledge base and knowledge graph

Recent advances in knowledge-graph-based research

focus on knowledge representation learning (KRL) or knowl-

edge graph embedding (KGE) by mapping entities and

relations into low-dimensional vectors while capturing their

semantic meanings. Speciﬁc knowledge acquisition tasks

include knowledge graph completion (KGC), triple classiﬁca-

tion, entity recognition, and relation extraction. Knowledge-

aware models beneﬁt from the integration of heterogeneous

information, rich ontologies and semantics for knowledge

representation, and multi-lingual knowledge. Thus, many

real-world applications such as recommendation systems and

question answering have been brought about prosperity with

the ability of commonsense understanding and reasoning.

Some real-world products, for example, Microsoft’s Satori

and Google’s Knowledge Graph, have shown a strong

capacity to provide more efﬁcient services.

arXiv:2002.00388v1 [cs.CL] 2 Feb 2020

To have a comprehensive survey of current literatures,

this paper focuses on knowledge representation which

enriches graphs with more context, intelligence and se-

mantics for knowledge acquisition and knowledge-aware

applications. Our main contributions are summarized as

follows.

• Comprehensive review.

We conduct a comprehen-

sive review on the origin of knowledge graph and

modern techniques for relational learning on knowl-

edge graphs. Major neural architectures of knowledge

graph representation learning and reasoning are

introduced and compared. Moreover, we provide a

complete overview of many applications on different

domains.

• Full-view categorization and new taxonomies.

full-view categorization of research on knowledge

graph, together with ﬁne-grained new taxonomies are

presented. Speciﬁcally, in the high-level we review

knowledge graph in three aspects: KRL, knowledge

acquisition, and knowledge-aware application. For

KRL approaches, we further propose ﬁne-grained

taxonomies into four views including representa-

tion space, scoring function, encoding models, and

auxiliary information. For knowledge acquisition,

KGC is reviewed under embedding-based ranking,

relational path reasoning, logical rule reasoning and

meta relational learning; entity-relation acquisition

tasks are divided into entity recognition, typing, dis-

ambiguation, and alignment; and relation extraction

is discussed according to the neural paradigms.

• Wide coverage on emerging advances.

Knowledge

graph has experienced rapid development. This sur-

vey provides a wide coverage on emerging topics

including transformer-based knowledge encoding,

graph neural network (GNN) based knowledge prop-

agation, reinforcement learning based path reasoning,

and meta relational learning.

• Summary and outlook on future directions.

This

survey provides a summary on each category and

highlights promising future research directions.

The remainder of this survey is organized as follows:

ﬁrst, an overview of knowledge graphs including history,

notations, deﬁnitions and categorization is given in Section 2;

then, we discuss KRL in Section 3 from four scopes; next, our

review goes to tasks of knowledge acquisition and temporal

knowledge graphs in Section 4 and Section 5; downstream

applications are introduced in Section 6; ﬁnally, we discuss

future research directions, together with a conclusion in the

end. Other information, including KRL model training and

a collection of knowledge graph datasets and open-source

implementations can be found in the appendices.

2 OVERVIEW

2.1 A Brief History of Knowledge Bases

Knowledge representation has experienced a long-period

history of development in the ﬁelds of logic and AI. The

idea of graphical knowledge representation ﬁrstly dated

back to 1956 as the concept of semantic net proposed by

Richens [1], while the symbolic logic knowledge can go

back to the General Problem Solver [2] in 1959. The knowl-

edge base is ﬁrstly used with knowledge-based systems

for reasoning and problem solving. MYCIN [3] is one of

the most famous rule-based expert systems for medical

diagnosis with a knowledge base of about 600 rules. Later,

the community of human knowledge representation saw

the development of frame-based language, rule-based, and

hybrid representations. Approximately at the end of this

period, the Cyc project

began, aiming at assembling human

knowledge. Resource description framework (RDF)

and

Web Ontology Language (OWL)

were released in turn, and

became important standards of the Semantic Web

. Then,

many open knowledge bases or ontologies were published

such as WordNet, DBpedia, YAGO, and Freebase. Stokman

and Vries [4] proposed a modern idea of structure knowledge

in a graph in 1988. However, it was in 2012 that the concept

of knowledge graph gained great popularity since its ﬁrst

launch by Google’s search engine

, where the knowledge

fusion framework called Knowledge Vault [5] was proposed

to build large-scale knowledge graphs. A brief road map of

knowledge base history is illustrated in Appendix A

2.2 Deﬁnitions and Notations

Most efforts have been made to give a deﬁnition by de-

scribing general semantic representation or essential char-

acteristics. However, there is no such wide-accepted formal

deﬁnition. Paulheim [6] deﬁned four criteria for knowledge

graphs. Ehrlinger and W

oß [7] analyzed several existing

deﬁnitions and proposed Deﬁnition 1 which emphasizes the

reasoning engine of knowledge graphs. Wang et al. [8] pro-

posed a deﬁnition as a multi-relational graph in Deﬁnition 2.

Following previous literature, we deﬁne a knowledge graph

G = {E, R, F}

, where

and

are sets of entities,

relations and facts, respectively. A fact is denoted as a triple

(h, r, t) ∈ F.

Deﬁnition 1

(Ehrlinger and W

oß [7])

A knowledge graph

acquires and integrates information into an ontology and

applies a reasoner to derive new knowledge.

Deﬁnition 2

(Wang et al. [8])

A knowledge graph is a multi-

relational graph composed of entities and relations which are

regarded as nodes and different types of edges, respectively.

Speciﬁc notations and their descriptions are listed in

Table 1. Details of several mathematical operations are

explained in Appendix B.

2.3 Categorization of Research on Knowledge Graph

This survey provides a comprehensive literature review on

the research of knowledge graphs, namely KRL, knowledge

acquisition, and a wide range of downstream knowledge-

aware applications, where many recent advanced deep

learning techniques are integrated. The overall categorization

of the research is illustrated in Fig. 2.

1. http://cyc.com

Released as W3C recommendation in 1999 available at http://w3.

org/TR/1999/REC-rdf-syntax-19990222.

3. http://w3.org/TR/owl-guide

4. http://w3.org/standards/semanticweb

http://blog.google/products/search/

introducing-knowledge-graph-things-not

of 25

免费下载

知识图谱

文档被以下合辑收录

数智化医疗内容合集（共73篇）

数字化医疗内容收集

关注

文档被以下合辑收录

评论