Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 5145 |
| 2026-08-02 | 5145 |
| 2026-08-06 | 5145 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# awesome-knowledge-graph
整理知识图谱相关学习资料，提供系统化的知识图谱学习路径。
---
## 目录
- [理论及论文](#理论及论文)
- [图谱及数据集](#图谱及数据集)
- [工具及服务](#工具)
- [白皮书及报告](#白皮书及报告)
- [机构及人物](#机构及人物)
- [视频课程](#视频课程)
- [专栏合集](#专栏合集)
- [评测竞赛](#评测竞赛)
- [项目案例](#项目案例)
- [推广技术文章](#推广技术文章)
<!-- /MarkdownTOC -->
## 理论及论文
### 整体概念架构
随着知识图谱的发展，与之相关的概念也越来越多，在阅读论文时先准确的把握该论文所要解决问题处于的层级或者位置对于更好的理解论文也比较有帮助，在此对知识图谱的概念进行了总结整理，整体概念架构图如下图所示，后面的论文分类也按照该整体架构概念图从顶向下，从整体到细节的方式组织。
### 综述综合
#### 大综述
- [Knowledge Graph Construction Techniques](./paper/知识图谱构建技术综述_刘峤.caj)
- [Review on Knowledge Graph Techniques (2016)](./paper/知识图谱技术综述.pdf)[一篇经典的中文综述，适合入门。]
- [Reviews on Knowledge Graph Research (2017)](./paper/知识图谱研究综述-李涓子.pdf)[清华大学李娟子老师的综述，十分经典，对知识图谱走入大众视野功不可没。]
- [The Research Advances of Knowledge Graph (2017)](./paper/知识图谱研究进展_漆桂林.caj)[东南大学漆桂林老师的综述，也是2017年发表的，同样对知识图谱走入大众视野起到很大作用。]
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications (2020)](https://arxiv.org/pdf/2002.00388.pdf)
- [Knowledge Graphs (2020)](https://arxiv.org/pdf/2003.02320.pdf)[2020年初的一篇作者众多、内容很全的综述，适合系统性的建立知识图谱的知识体系。]
#### Knowledge-Augmented LMs(知识增强语言模型)
知识图谱增强语言模型是最近两年比较流行，主要发生在BERT出来之后，将知识先验信息融入到语言模型，可以说是知识图谱助力NLP十分关键的一环，将该专题放在比较靠前的位置。
- [ERNIE: Enhanced Representation through Knowledge Integration(2019)](https://arxiv.org/abs/1904.09223)[百度版本ERNIE，在预训练阶段Mask Token时引入了Entity级别和Phase级别，似的模型在学习时能够将某些特定知识作为一个整体进行学习。]
- [ERNIE: Enhanced Language Representation with Informative Entities(2019)](https://arxiv.org/abs/1905.07129)[清华版本ERNIE，将从句子中识别出的Entity的Embedding与原句子Embedding同时K-Encoder新设计的模块，在该模块中也采用多头注意力机制之后融合编码在分别输出到下一层。]
- [Latent Relation Language Models(2019)](https://arxiv.org/pdf/1908.07690.pdf)[将文本中实体在知识图谱中的结构作为条件建模到概率语言模型中。]
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://arxiv.org/pdf/1909.07606.pdf)
- [KG-BERT: BERT for Knowledge Graph Completion(2019)](https://arxiv.org/abs/1909.03193)[与ERNIE系列处理的问题正好相反，是将Bert的模型应用到知识图谱的补全任务中，根据h,r->t,h,r,t->{0,1}的任务特点设计出两个fine-tuning任务。]
- [Enriching BERT with Knowledge Graph Embeddings for Document Classification(2019)](https://arxiv.org/abs/1909.08402)[结合Bert和知识图谱embedding应用到具体的文档分类任务，将Bert输出、人工设计的Meta特征、作者的kg embedding进行concat之后输入mlp进行分类。]
- [ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding
](https://arxiv.org/pdf/1907.12412.pdf)
- [SENSEMBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation](https://pasinit.github.io/papers/scarlini_etal_aaai2020.pdf)
- [Inducing Relational Knowledge from BERT](https://arxiv.org/pdf/1911.12753.pdf)
- [Integrating Graph Contextualized Knowledge into Pre-trained Language Models](https://arxiv.org/pdf/1912.00147.pdf)
- [Enhancing Pre-Trained Language Representations with Rich Knowledge
for Machine Reading Comprehension](https://www.aclweb.org/anthology/P19-1226.pdf)
- [K-ADAPTER- Infusing Knowledge into Pre-Trained Models with Adapters](https://arxiv.org/pdf/2002.01808)
- [Knowledge Enhanced Contextual Word Representations (EMNLP 2019)](https://arxiv.org/abs/1909.04164)
- [KEPLER: A Unified Model for Knowledge Embedding and
Pre-trained Language Representation (2020)](https://arxiv.org/pdf/1911.06136.pdf)
- [Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model (ICLR 2020)](https://arxiv.org/abs/1912.09637)[在预训练任务中结合wikepedia知识将句子中的实体替换为同类型的其他实体，使预训练模型能够在很少的训练数据甚至是无训练数据的情况下在某些特定QA任务取得不错的效果。]
- [Language Models as Knowledge Bases?](https://arxiv.org/pdf/1909.01066.pdf)[设计出一种基于完形填空任务的探测结构LAMA验证了类BERT预研模型具备一定的知识库能力]
- [A Frame-based Sentence Representation for Machine Reading Comprehension (ACL 2020)](https://www.aclweb.org/anthology/2020.acl-main.83.pdf)[将句子中包含的FrameNet信息自动标注出来之后，平铺展开填充形成quadruples，再将quadruples采用不同的Aggregation Model表示为句子表示，然后采用BERT等神经网络进行编码进行后续的阅读理解任务。]
#### 常识图谱(Commonsense)
目前人工智能在很多方面表现的比较智障的原因，很多学者仍为是由于AI缺乏基本常识知识的原因，因此，从感知智能到认知智能常识知识起着很重要的作用，而常识图谱作为常识知识的一个重要表示手段也越来越受到重视。
- [KILT: a Benchmark foExcerpt of 22,545 characters
Read on GitHub
48
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:017abc81a9b032c3, name:knowledge graph