浙江大学最新《知识图谱》课程，八堂课全面讲述识图谱的基本概念、核心技术内涵和应用实践方法

2022 年 1 月 13 日 专知

知识图谱的早期理念源于万维网之父 Tim Berners Lee 关于语义网(The Semantic Web) 的设想，旨在采用图的结构(Graph Structure)来建模和记录世界万物之间的关联关系和知识，以便有效实现更加精准的对象级搜索。经过近二十年的发展，知识图谱的相关技术已经在搜索引擎、智能问答、语言及视觉理解、大数据决策分析、智能设备物联等众多领域得到广泛应用，被公认为是实现认知智能的重要基石。近年来，随着自然语言处理、深度学习、图数据处理等众多领域的飞速发展，知识图谱在自动化知识获取、基于知识的自然语言处理、基于表示学习的机器推理、基于图神经网络的图挖掘与分析等领域又取得了很多新进展。

本课程是面向浙江大学研究生开设的专业选修课程。课程系统性介绍知识图谱的基本概念、核心技术内涵和应用实践方法，具体内容涉及知识表示与推理、图数据库、关系抽取与知识图谱构建、知识图谱表示学习与嵌入、语义搜索与知识问答、图神经网络与图挖掘分析等。课程内容的设计以“基础、前沿与实践”相结合为基本原则，既包括基本概念介绍和实践应用内容，也包括学术界的最新前沿进展的介绍。

Descriptons	Suggested Readings
第一讲：知识图谱概述 Lecture 00 、 Lecture 01	知识图谱的系统工程观（2018） Industry-Scale Knowledge Graphs:Lessons and Challenges （2019）CCCF译文 \| 工业级知识图谱：经验与挑战 The Semantic Web（2001）
第二讲：知识图谱的表示与建模 Lecture 02 Tutorials & Tools: Protégé Sample codes: TransE (preview) DistMult	What is a Knoweldge Representation. AI Magazine (1993) 知识图谱-浅谈RDF、OWL、SPARQL 知识表示学习研究进展. 计算机研究与发展（2016） Knowledge Graph Embedding: A Survey of Approaches and Applications. TKDE (2017) A Description Logic Primer. (2013)
第三讲：知识图谱的存储与查询 Lecture 03 Tutorials & Tools：Neo4j ( Sampledata) gStore、Jena	知识图谱数据管理研究综述. 软件学报. （2019）数据库视角下的知识图谱研究. CCKS2019顶会Review (2019) RDF data storage and query processing schemes: A survey. ACM Computing Surveys (2018) Foundations of modern query languages for graph databases. ACM Computing Surveys (2016)
第四讲：知识图谱的获取与抽取 Lecture 04 Tutorials & Tools: DeepKE Sample codes: CNN/PCNN, GCN, BERT	Semantic Relation Extraction from Text. CCKS2018 Tutorial Relation Extraction : A Survey (2017) Relation Extraction Using Distant Supervision: A Survey ACM Computing Surveys (2019) 知识图谱从哪里来：实体关系抽取的现状与未来 (2019) Matching the Blanks: Distributional Similarity for Relation Learning (ACL2019) Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks (NAACL2019) Simple BERT Models for Relation Extraction and Semantic Role Labeling (2019) Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (EMNLP2018)
第五讲：知识图谱与机器推理 Lecture 05 Tutorials & Tools: Jena , Drools Sample codes: AMIE, ANALOGY, ComplEx	面向知识图谱的知识推理研究进展. 软件学报（2018） A Review of Relational Machine Learning for Knowledge Graphs. (Procedding of IEEE 2015) Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning. (WWW2019) DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. (EMNLP2017) Fast rule mining in ontological knowledge bases with AMIE+. (VLDBJ 2015) Differentiable Learning of Logical Rules for Knowledge Base Reasoning. (NIPS2017) Knowledge Representation and Reasoning on the Semantic Web: OWL. (2011) (Advanced) Representing Ontologies Using Description Logics, Description Graphs, and Rules. (Artificial Intelligence. 2009)
第六讲：知识图谱与智能问答 Lecture 06 Tutorials & Tools: gAnswer	《智能问答》. 高等教育出版社（2018） Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. (ACL2015) Improved Neural Relation Detection for Knowledge Base Question Answering. (ACL2017) Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs. (2019) Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. (ICLR2018) UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering. (NAACL2019) Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader. (ACL2019) Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering. (NAACL2019)
第七讲：知识图谱与图网络算法 Lecture 07 Sample codes: Deepwalk, GCN, GAT	Representation Learning on Networks. WWW2019 Tutorials Deep Learning for Graphs. CCKS2019 Tutorials Graph Neural Networks: A Review of Methods and Applications Inductive Representation Learning on Large Graphs. NIPS2017 Deep Graph Infomax. ICLR2019 Heterogeneous Graph Attention Network. WWW2019 End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion. AAAI2019 On the Equivalence between Node Embeddings and Structural Graph Representations. ICLR2020
第八讲：知识图谱新发展和新应用 Lecture 08