Semantic search
Retrieval based on the meaning of a query and documents rather than literal keyword matching, using entities, context and learned…
Algorithms
Hummingbird
Google's 2013 rewrite of its core ranking infrastructure, shifting emphasis from individual keywords toward the meaning of whole queries.
In full
Hummingbird was an architectural replacement rather than a filter, enabling query rewriting, synonym handling and conversational query understanding, and paving the way for entity-centric search alongside the Knowledge Graph. Google now lists it among retired systems because its capabilities were absorbed into successor systems. Its conceptual legacy is that pages answer questions, not keyword strings.
Example
'Where can I buy an iPhone charger near me' began returning local retailers rather than pages containing that exact phrase.
Related terms
RankBrain
Google's first machine-learning ranking system, introduced in 2015, which helps interpret how queries relate to concepts, especially…
BERT
A transformer language model Google applied to search from 2019, improving understanding of word order, prepositions and context within…
Knowledge Graph
Google's database of entities and the relationships between them, used to disambiguate queries, power knowledge panels and ground…
Google ranking systems
Google's documented list of the systems that generate rankings, distinguished from one-off 'updates' to those systems, and including…