Semantic search denotes search with meaning, as distinguished from lexical search where the search engine looks for literal matches of the query words or variants of them, without understanding the overall meaning of the query.[1] Semantic search is an approach toinformation retrieval that seeks to improvesearch accuracy by understandingthe searcher's intent and thecontextual meaning of terms as they appear in the searchable dataspace, whether on theWeb or within a closed system, to generate more relevant results. Modern semantic search systems often use vector embeddings to represent words, phrases, or documents as numerical vectors, allowing the retrieval engine to measure similarity based on meaning rather than exact keyword matches.[2][3]
Some authors regard semantic search as a set of techniques for retrieving knowledge from richly structured data sources likeontologies andXML as found on theSemantic Web.[4] Such technologies enable the formal articulation ofdomain knowledge at a high level of expressiveness and could enable the user to specify their intent in more detail at query time.[5] The articulation enhances content relevance and depth by including specific places, people, or concepts relevant to the query.
Tools like Google'sKnowledge Graph provide structured relationships between entities to enrich query interpretation.[6]
Models likeBERT and Sentence-BERT convert words or sentences into dense vectors for similarity comparison.[7]
Semantic ontologies likeWeb Ontology Language,Resource Description Framework, andSchema.org organize concepts and relationships, allowing systems to infer related terms and deeper meanings.[8]
Hybrid search models combinelexical retrieval (e.g., BM25) withsemantic ranking using pretrained transformer models for optimal performance.[9]
 | This Internet-related article is astub. You can help Wikipedia byadding missing information. |