nlp:knowledge_graphs
Table of Contents
Knowledge Graphs
Overviews
- Knowledge Graphs
- Knowledge Graph Completion
Knowledge Graph Construction
See also Relation Extraction.
KG Construction using LLMs
- Github: 2024 - The Graph Maker Given an ontology and text, constructs an KG. There doesn't seem to be a paper for this system.
Knowledge Graph Completion
- DistMult, ConvE, MINERVA, etc (see related work of Bansal 2019)
Text-Enhanced Knowledge Graph Extension
This is a relatively unexplored area, see Wood 2021 (NAACL 2021 Video).
- Yao et al 2019 - KG-BERT: BERT for Knowledge Graph Completion Says “most knowledge graph embedding models only use structure information in observed triple facts, which suffer from the sparseness of knowledge graphs. Some recent studies incorporate textual information to enrich knowledge representation (Socher et al. 2013; Xie et al. 2016; Xiao et al. 2017), but they learn unique text embedding for the same entity/relation in different triples, which ignore contextual information.”
- Wood et al 2021 - Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction Builds upon OpenKI. Says “Relation prediction informed from a combination of text corpora and curated knowledge bases, combining knowledge graph completion with relation extraction, is a relatively little studied task.”
Applications of Knowledge Graphs
- Reasoning With Knowledge Graphs
- In AI Agents
Software
Related Pages
- Extracting Knowledge from Language Models (Language models as knowledge bases)
nlp/knowledge_graphs.txt · Last modified: 2025/06/27 23:05 by jmflanig