The authoritative reference for semantic AI terminology. Every term defined with depth, context, and real-world examples.
A business abstraction that defines the meaning of data for AI and analytics systems.
A formal representation of knowledge as a set of concepts, entities, and their relationships.
A network of entities and their semantic relationships, enabling machines to understand context.
Search that understands the meaning and intent behind a query, not just keyword matching.
Numerical representations of text, images, or data that capture semantic meaning in high-dimensional space.
An AI architecture that grounds language model responses in retrieved, factual documents.
An open standard for connecting AI models to external data sources and tools with semantic context.
A measure of how alike two pieces of text are in meaning, regardless of exact wording.
The gradual change in the meaning of a term or data definition across systems or over time.
The process of identifying and linking records that refer to the same real-world entity across datasets.
An architecture that provides unified, intelligent data access across distributed, heterogeneous environments.
An extension of SQL that allows querying data using business concepts rather than raw table structures.
The process of finding correspondences between concepts in different ontologies to enable interoperability.
The proliferation of incompatible semantic definitions across an organization's data systems.
A specialized database for storing and querying RDF triples — the building blocks of knowledge graphs.
The standard query language for retrieving and manipulating data stored in RDF format.
The W3C standard data model for representing information as subject-predicate-object triples.
The W3C standard language for defining rich, expressive ontologies with logical reasoning capabilities.
An NLP task that identifies and classifies named entities — people, organizations, locations — in text.
The ability of systems to exchange data and preserve the meaning of that data across boundaries.
Tim Berners-Lee's vision of a web where data is machine-readable and universally linked by meaning.
A set of best practices for publishing structured data on the web so it can be interconnected and queried.
A JSON-based format for encoding Linked Data, enabling semantic annotations in web pages and APIs.
A collaborative vocabulary for structured data markup on web pages, supported by Google, Microsoft, and Yahoo.
A database optimized for storing and querying high-dimensional vector embeddings at scale.
A caching strategy that stores and retrieves AI responses based on semantic similarity rather than exact query matching.
Techniques for representing knowledge graph entities and relations as dense vectors for machine learning.
The process of tagging text or data with references to formal ontologies to make meaning machine-readable.
A decentralized data architecture where domain teams own and serve their data as products.
A system for managing changes to data schemas and definitions using meaningful version numbers.
AI systems that combine neural network learning with symbolic reasoning for more reliable, explainable intelligence.
An NLP task that identifies the semantic roles of words in a sentence — who did what to whom.
The NLP task of determining which meaning of a word is intended in a given context.
Converting natural language into formal, machine-executable representations like SQL, SPARQL, or logical forms.
The phenomenon where the statistical properties of a target variable change over time, degrading ML model performance.
A two-stage retrieval technique that uses a cross-encoder to re-score and reorder initial search results for precision.
An advanced RAG architecture that uses knowledge graphs to improve retrieval accuracy and multi-hop reasoning.
Microsoft's open-source SDK for building AI agents that combine LLMs with semantic plugins and memory.
A curated, standardized set of terms used to index, catalog, and retrieve information consistently.
A family of technologies — RDF, OWL, SPARQL, ontologies — that enable machines to understand meaning.
When an AI model generates confident, plausible-sounding but factually incorrect or fabricated information.
The practice of connecting multiple semantic layers across systems into a unified, queryable semantic fabric.
AI technology that converts natural language questions into SQL queries for database retrieval.
An AI memory system that stores and retrieves information based on meaning and semantic similarity.
The field of AI concerned with how to formally encode knowledge so machines can reason with it.
Design principles that use meaningful, consistent language and structure to make interfaces more intuitive.