User Tools

Site Tools


nlp:knowledge_graphs

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
nlp:knowledge_graphs [2021/06/09 18:19] – [Overviews] jmflanignlp:knowledge_graphs [2025/06/27 23:05] (current) – [Knowledge Graph Construction] jmflanig
Line 3: Line 3:
 ===== Overviews ===== ===== Overviews =====
   * Knowledge Graphs   * Knowledge Graphs
 +    * [[https://arxiv.org/pdf/1503.00759.pdf|Nickel et al 2015 - A Review of Relational Machine Learning for Knowledge Graphs]]
     * [[https://arxiv.org/pdf/2002.00388.pdf|Gi et al 2020 - A Survey on Knowledge Graphs: Representation, Acquisition and Applications]]     * [[https://arxiv.org/pdf/2002.00388.pdf|Gi et al 2020 - A Survey on Knowledge Graphs: Representation, Acquisition and Applications]]
   * Knowledge Graph Completion   * Knowledge Graph Completion
Line 11: Line 12:
 See also [[Relation Extraction]]. See also [[Relation Extraction]].
   * [[https://arxiv.org/pdf/2006.13473.pdf|Dong et al 2020 - AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types]]   * [[https://arxiv.org/pdf/2006.13473.pdf|Dong et al 2020 - AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types]]
 +  * [[https://arxiv.org/pdf/2010.03824.pdf|Hope et al 2021 - Extracting a Knowledge Base of Mechanisms from COVID-19 Papers]]
 +
 +==== KG Construction using LLMs ====
 +  * Github: [[https://github.com/rahulnyk/graph_maker|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 ==== ==== Knowledge Graph Completion ====
 +  * TransE: [[https://proceedings.neurips.cc/paper/2013/file/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf|Bordes et al 2016 - Translating Embeddings for Modeling Multi-relational Data]]
 +  * DistMult, ConvE, MINERVA, etc (see related work of [[https://www.aclweb.org/anthology/P19-1431.pdf|Bansal 2019]])
   * [[https://www.aclweb.org/anthology/P19-1431.pdf|Bansal et al 2019 - A2N: Attending to neighbors for knowledge graph inference]]   * [[https://www.aclweb.org/anthology/P19-1431.pdf|Bansal et al 2019 - A2N: Attending to neighbors for knowledge graph inference]]
   * [[https://arxiv.org/pdf/2010.03548.pdf|Das et al 2020 - Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion]]   * [[https://arxiv.org/pdf/2010.03548.pdf|Das et al 2020 - Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion]]
Line 18: Line 25:
 ==== Text-Enhanced Knowledge Graph Extension ==== ==== Text-Enhanced Knowledge Graph Extension ====
 This is a relatively unexplored area, see [[https://www.aclweb.org/anthology/2021.naacl-main.268/|Wood 2021]] ([[https://underline.io/events/122/sessions/4218/lecture/19571-integrating-lexical-information-into-entity-neighbourhood-representations-for-relation-prediction|NAACL 2021 Video]]). This is a relatively unexplored area, see [[https://www.aclweb.org/anthology/2021.naacl-main.268/|Wood 2021]] ([[https://underline.io/events/122/sessions/4218/lecture/19571-integrating-lexical-information-into-entity-neighbourhood-representations-for-relation-prediction|NAACL 2021 Video]]).
-  * [[https://www.aclweb.org/anthology/2021.naacl-main.268.pdf|Wood et al 2021 - Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction]]+  * [[https://arxiv.org/pdf/1904.12606.pdf|Zhang et al 2019 - OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference]] 
 +  * [[https://arxiv.org/pdf/1909.03193.pdf|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." 
 +  * [[https://www.aclweb.org/anthology/2021.naacl-main.268.pdf|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."
  
-===== Reasoning With Knowledge Graphs ===== +===== Applications of Knowledge Graphs ===== 
-  * [[https://arxiv.org/pdf/2006.14198.pdf|Das et al 2020 - A Simple Approach to Case-Based Reasoning in Knowledge Bases]]+  * **Reasoning With Knowledge Graphs** 
 +    * [[https://arxiv.org/pdf/2006.14198.pdf|Das et al 2020 - A Simple Approach to Case-Based Reasoning in Knowledge Bases]] 
 +    * [[https://arxiv.org/pdf/2505.21926|Hua et al 2025 -  Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning]] 
 +  * **In AI Agents** 
 +    * [[https://arxiv.org/pdf/2501.13956|Rasmussen et al 2025 - Zep: A Temporal Knowledge Graph Architecture for Agent Memory]]
  
 ===== Software ===== ===== Software =====
Line 28: Line 41:
 ===== Related Pages ===== ===== Related Pages =====
   * [[Information Extraction]]   * [[Information Extraction]]
 +  * [[Knowledge-Enhanced Methods]]
 +  * [[nlp:language_model#Extracting Knowledge from Language Models]] (Language models as knowledge bases)
 +  * [[Natural Language Interfaces to Databases]]
 +  * [[Ontology Learning]]
  
nlp/knowledge_graphs.1623262793.txt.gz · Last modified: 2023/06/15 07:36 (external edit)

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki