Construction of Knowledge Graphs: State and Challenges
arXiv:2302.11509 · doi:10.3390/info15080509
Abstract
With knowledge graphs (KGs) at the center of numerous applications such as recommender systems and question answering, the need for generalized pipelines to construct and continuously update such KGs is increasing. While the individual steps that are necessary to create KGs from unstructured (e.g. text) and structured data sources (e.g. databases) are mostly well-researched for their one-shot execution, their adoption for incremental KG updates and the interplay of the individual steps have hardly been investigated in a systematic manner so far. In this work, we first discuss the main graph models for KGs and introduce the major requirement for future KG construction pipelines. Next, we provide an overview of the necessary steps to build high-quality KGs, including cross-cutting topics such as metadata management, ontology development, and quality assurance. We then evaluate the state of the art of KG construction w.r.t the introduced requirements for specific popular KGs as well as some recent tools and strategies for KG construction. Finally, we identify areas in need of further research and improvement.
arXiv comment51 pages, 5 figures, 4 tables, 328 references
References in corpus (42)
- Distributed Representations of Words and Phrases and their Compositionality
- Overcoming catastrophic forgetting in neural networks
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Language Models are Few-Shot Learners
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- KGAT: Knowledge Graph Attention Network for Recommendation
- A Review of Relational Machine Learning for Knowledge Graphs
- A Survey on Deep Learning for Named Entity Recognition
- Scaling Instruction-Finetuned Language Models
- Unifying Large Language Models and Knowledge Graphs: A Roadmap
- KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
- Deep Entity Matching with Pre-Trained Language Models
- Multi-Modal Knowledge Graph Construction and Application: A Survey
- A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
- The Gremlin Graph Traversal Machine and Language
- The Future is Big Graphs! A Community View on Graph Processing Systems
- BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis
- Neural Networks for Entity Matching: A Survey
- OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
- Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
- HoloDetect: Few-Shot Learning for Error Detection
- Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning
- WorldKG: A World-Scale Geographic Knowledge Graph
- Directly Mapping RDF Databases to Property Graph Databases
- PG-Schema: Schemas for Property Graphs
- CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
- SDM-RDFizer: An RML Interpreter for the Efficient Creation of RDF Knowledge Graphs
- AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
- OLaLa: Ontology Matching with Large Language Models
- Inductive Relation Prediction by Subgraph Reasoning
- AutoBlock: A Hands-off Blocking Framework for Entity Matching
- From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management
- Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale
- Decentralized Collaborative Knowledge Management using Git
- Neural Compositional Rule Learning for Knowledge Graph Reasoning
- NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
- Improving Continual Relation Extraction through Prototypical Contrastive Learning
- StaTIX - Statistical Type Inference on Linked Data
- Order Matters: Matching Multiple Knowledge Graphs
- Datalog Reasoning over Compressed RDF Knowledge Bases
- Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering
- Gollum: A Gold Standard for Large Scale Multi Source Knowledge Graph Matching