Lexical Search
Definition
Lexical search finds documents based on explicit words, word stems, or term-based relevance signals.
Methods like BM25 weight terms by frequency and rarity. They are suitable for exact terms, IDs, and technical terms. Without synonym expansion or additional semantic methods, purely lexical matching does not automatically capture synonyms.
Simply explained
How to search by the actual words occurring instead of only by meaning.
Why it matters in practice
Word-based search remains important for corporate documents and can be combined with semantic methods into a hybrid search.
Example from business
A spare parts search uses BM25 for exact part numbers and product names.
Limits and pitfalls
- Dismiss lexical search as outdated; ignore tokenization and language; use vector search only for IDs.
Origin & history
Term-based information retrieval methods form the basis of classical search engines; BM25 became widespread from the 1990s onward.
Use in mid-sized companies
- Possible application in SMEs: Combine exact search for IDs, technical terms, and documented phrases with semantic search.
Frequently asked questions
When is lexical search useful?
For exact terms and identifiers. What are the limits? Synonyms and implicit meaning require appropriate extensions.
Sources
- Introduction to Information Retrieval · Manning et al., Introduction to Information Retrieval
- Ergänzender Primärbeleg · Ergänzender Primärbeleg
- Ergänzender Primärbeleg · Ergänzender Primärbeleg
Source verification: 10./12.10.2026.
Editorially reviewed on: