Knowledge Tree
semi-structured data
Facts (13)
Sources
Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org 9 facts
referenceRyen et al. (2022) reviewed methods for building semantic knowledge graphs from semi-structured and structured data.
referenceAssche et al. (2023) conducted a systematic literature review on declarative RDF graph generation from heterogeneous semi-structured and structured data.
claimKnowledge graphs integrate heterogeneous data from various sources, including unstructured data (text), semi-structured data (pictures, audio), and structured data (databases or other knowledge graphs) in a semantically rich manner.
procedureExtraction methods for semi-structured data typically combine data cleaning and rule-based mappings to transform input data into a knowledge graph, targeting defined classes and relations of an existing ontology.
claimWhile entity resolution typically operates on semi-structured data, deep learning-based approaches have been developed to address entity resolution in unstructured data sources.
claimKnowledge extraction methods are necessary to transform semi-structured and unstructured data into structured entities, relations, and the knowledge graph data model.
claimKnowledge graph construction requires scalable methods for the acquisition, transformation, and integration of diverse input data, including structured, semi-structured, and multimodal unstructured data such as textual documents, web data, images, and videos.
referenceHogan et al. provide a comprehensive introduction to knowledge graphs, covering multiple graph data models, methods for handling unstructured, semi-structured, and structured data, as well as tasks like learning on and publishing knowledge graphs.
measurementPopulating knowledge graphs from semi-structured data is the most common method, while only approximately 50% of the considered solutions or toolsets support importing from unstructured or structured data.
Enterprise AI Requires the Fusion of LLM and Knowledge Graph stardog.com Dec 4, 2024 4 facts
referenceStardog Voicebox supports any database, document, or API, including structured, semi-structured, and unstructured data.
referenceSafety RAG supports any database, document, or API, including structured, semi-structured, and unstructured data.
claimEnterprise AI platforms require the fusion of Large Language Models (LLMs) and Knowledge Graphs (KGs) to achieve comprehensive recall, where LLMs process unstructured data like documents and KGs process structured and semi-structured data like database records.
referenceGeneric Graph RAG (Retrieval-Augmented Generation) considers structured data but lacks a principled unification of structured, semi-structured, and unstructured data sources across an enterprise.