Semantic Search

TL;DR — Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. means search engines match the meaning of what you’re looking for, not just the exact words you typed. Google figures out “what does this person actually want?” and “what is this page really about?” — then connects the two. It’s why you don’t have to repeat keywords over and over anymore, and why writing naturally about a topic works better than stuffing it with phrases.

What semantic search is

Semantic search seeks matches based on meaning and context in addition to exact terms. Evidence for this claim BERT learns bidirectional contextual language representations that can be fine-tuned for search-relevant language tasks. Scope: BERT research; semantic retrieval systems may use many other models and signals. Confidence: high · Verified: 2026-07-14 Devlin et al.: BERT Modern systems may combine language models, lexical retrieval, entities, and other signals rather than rely on one technique. Evidence for this claim Google reported using BERT to better understand language and context in some Search queries. Scope: Google Search's documented rollout; it does not mean lexical matching was replaced or disclose the full ranking system. Confidence: high · Verified: 2026-07-14 Google: Understanding searches better than ever before

For a long time, search engines mostly counted words. If you searched “cheap flights,” they looked for pages with the words “cheap” and “flights” on them. Useful, but dumb — it had no idea that “affordable airfare” means the same thing, or that “jaguar” could be an animal or a car.

Semantic search fixes that. Instead of matching letters and words, it tries to understand meaning. Two ideas drive it:

• Understanding what you mean. Google reads your whole query as a sentence, not a bag of keywords. It works out your intent — are you trying to buy something, learn something, or find a specific site?
• Understanding what a page is about. It figures out the topics a page covers and the real-world things (people, places, products) it mentions — not just which words appear.

A good way to picture it: searching “how to fix a leaky faucet” and “repairing a dripping tap” should return the same results, even though those phrases share almost no words. To a keyword engine they look unrelated. To a semantic engine they mean the same thing.

Why it changed SEO

When Google understood meaning, a lot of old tricks stopped working:

• You don’t need to stuff keywords. Google already knows synonyms and related terms. Repeating “best running shoes” twenty times doesn’t help — it can hurt.
• You don’t need a separate page for every wording. “Python tutorial,” “Python guide,” and “learn Python” all mean roughly the same thing, so Google picks one page to rank for all of them. Splitting them across pages just competes with yourself.
• Covering a topic well beats hitting a keyword count. A page that genuinely answers a question — with the related details a reader would want — outperforms one that just mentions the keyword a lot.

The thing most people get wrong

Semantic search does not mean keywords are dead. Keyword research still tells you what people search for and how often. What died is keyword stuffing and the idea that you must repeat exact phrases. And to be clear: “LSI keywords” are not a real thing. Google’s John Mueller said so directly. Sprinkling “semantically related keywords” from a tool isn’t how this works — covering the topic naturally is.

Want the full history (Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself., Hummingbird, RankBrain, BERT, MUM) and the technical detail of how it works? Switch to the Advanced tab.

TL;DR — Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. retrieves by meaning, not exact keyword match. Google built it in layers — Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. (2012), Hummingbird (2013), RankBrain (2015), neural matching (2018), BERT (2019), MUM (2021) — each solving a different piece (entities, whole-query meaning, novel queries, concept-level synonyms, contextual word meaning, multimodal reasoning). They augment keyword retrieval (BM25 still runs first at scale), they don’t replace it. Semantic search is the goal; vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one implementation. “LSI keywords” are a myth. The optimization answer hasn’t changed in a decade: natural language, topical depth, clear entities, intent alignment.

Keyword search vs. semantic search

Keyword and semantic retrieval are complementary, not mutually exclusive eras. Evidence for this claim BERT learns bidirectional contextual language representations that can be fine-tuned for search-relevant language tasks. Scope: BERT research; semantic retrieval systems may use many other models and signals. Confidence: high · Verified: 2026-07-14 Devlin et al.: BERT Google’s public explanations confirm language-understanding systems without revealing complete ranking weights. Evidence for this claim Google reported using BERT to better understand language and context in some Search queries. Scope: Google Search's documented rollout; it does not mean lexical matching was replaced or disclose the full ranking system. Confidence: high · Verified: 2026-07-14 Google: Understanding searches better than ever before

Classic retrieval ranks documents by term statistics. TF-IDF (term frequency × inverse document frequency) weights a word by how often it appears in a document against how rare it is across the corpus. BM25 (“Best Match 25”) refines that with length normalization and a saturation curve, and it’s still the dominant first-stage baseline in Elasticsearch, Solr, and Lucene — and inside Google and Bing. Powerful, fast, and entirely about words. It has no idea that “leaky faucet” and “dripping tap” mean the same thing.

Semantic search adds a layer of understanding on top:

The important framing: semantic search augments keyword retrieval rather than replacing it. At Google scale, an inverted-indexStoring a crawled page in the search index so it can appear in results. Crawled is not the same as indexed — Google selects what to keep, and indexing isn't guaranteed. BM25-style pass still does the high-recall first cut for speed, then neural systems re-rank and add documents that share concepts but not words. Pandu Nayak’s 2023 DOJ testimony described exactly this — an embeddingEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. system (internally RankEmbed) that “identifies a few more documents to add to those identified by the traditional retrieval.” Keyword retrieval didn’t die; it got a meaning-aware partner.

How Google built semantic search — the milestones

The evolution was incremental. No single update flipped Google from “keywords” to “meaning” — it was a decade of layers, each solving a distinct problem.

2012 — Knowledge Graph (“things, not strings”)

Google’s database of real-world entities and their relationships. Amit Singhal’s launch framing — “things, not strings” — is still the single best one-line explanation of the semantic shift. It launched with 500+ million entities and 3.5+ billion facts; the framing matters more than the numbers. This is what lets Google disambiguate “Taj Mahal” (monument, musician, or casino) and answer entity questions directly. The Knowledge Graph is the entity backbone the rest of the stack leans on — I go deeper on it in entity SEOEntity SEO is the practice of helping search engines and AI systems clearly identify, classify, and trust the entities you represent — your brand, your people, your products — rather than just matching keyword strings. The goal is to be an unambiguous, well-corroborated entity in machine knowledge systems so AI can cite you with confidence..

2013 — Hummingbird (whole-query meaning)

A complete rewrite of Google’s core query engine — not a tweak like Panda or Penguin, but a new engine. Singhal called it the most dramatic change since 2001. The goal was conversational and long-tail queries: paying attention to the whole query — the whole sentence, the meaning — rather than particular words. Danny Sullivan’s contemporaneous summary captures it well: Hummingbird “is paying more attention to each word in a query, ensuring that the whole query… is taken into account, rather than particular words.” Google says it affected 90% of searches. (It’s now listed as retired in the Ranking Systems Guide — superseded by the systems that evolved out of it.)

2015 — RankBrain (never-before-seen queries)

Machine learning applied to query interpretation. RankBrain’s job is the roughly 15% of daily queries Google had never seen before — it converts an unfamiliar query into a mathematical vector and finds conceptually similar queries it does understand. Greg Corrado, the Google scientist who confirmed it (via Bloomberg, not a Google blog post), described it as embedding “vast amounts of written language into mathematical entities — called vectors — that the computer can understand.” By 2016 it processed every query. Note the boundary: RankBrain maps unknown queries to known concepts; it’s not the same as BERT.

2018 — Neural matching (concept-level synonyms)

Where RankBrain related queries to concepts, neural matching extended concept-matching to the document side — connecting a query’s concepts to a page’s concepts even when they share no vocabulary. Danny Sullivan’s plain-language description is the best one out there: “Last few months, Google has been using neural matching, [an] AI method to better connect words to concepts. Super synonyms, in a way, and impacting 30% of queries.” The canonical example: “why does my television look strange” can surface results about the “soap opera effect” — a concept neither phrase names. (Internally, the 2023 DOJ testimony revealed this lineage as RankEmbed / RankEmbedBERT.)

2019 — BERT (contextual word meaning)

The big NLP breakthrough. BERT (Bidirectional Encoder Representations from Transformers) reads a word in context — looking at the words before and after it, rather than left-to-right one at a time. That’s what lets it catch how “to” changes the meaning of “2019 brazil traveler to usa need a visa” (a Brazilian traveling to the US, which older systems got backwards). Pandu Nayak called it the “biggest leap forward in the past five years, and one of the biggest leaps forward in the history of Search,” affecting 1 in 10 US English queries at launch and now nearly all of them. This is also the update SEOs most often misread: Danny Sullivan’s response was blunt — “There’s nothing to optimize for with BERT.”

2021 — MUM (multimodal, multilingual)

Multitask Unified Model — built on the T5 framework, trained across 75 languages, and able to understand information across text and images. Google says it’s 1,000× more powerful than BERT and, unlike BERT, can both understand and generate language. Important caveat: MUM is used for specific high-complexity cases (complex multi-step questions, certain featured snippets, shopping) — it was never Google’s general ranking engine, and it didn’t “replace” BERT.

2023+ — LLMs and AI search

Semantic retrieval now feeds generative answers. AI OverviewsAI Overviews are the AI-generated summary box Google shows above or within its regular search results, written by Gemini models from pages retrieved out of Google's normal Search index. It's a Search feature, not a separate platform or index. and AI Mode use the same meaning-based retrieval to find relevant passages, then an LLMA large language model (LLM) is a deep-learning model trained on massive text corpora to predict the next token and generate human-like text. LLMs use the transformer architecture and power AI search features like Google's AI Overviews (Gemini) and Bing Copilot (GPT-4). synthesizes an answer — see RAGRAG is the retrieve-then-generate pattern behind AI search: the system retrieves relevant passages from an external index at query time, injects them into the model's context, and generates an answer grounded in those sources — without changing the model's weights.. The semantic layer determines what gets retrieved and cited; the model just writes it up.

Semantic search vs. vector search

These get blurred constantly, so be precise:

• Semantic search is the goal — retrieve by meaning and intent.
• Vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one implementation — represent queries and documents as dense vectors and find nearest neighbors by cosine distance.

Vector search is the most common modern implementation, but it isn’t the only path to semantic search: query expansion, synonym rules, Knowledge Graph lookups, and entity recognition all get you there without computing a single embedding. Think of semantic search as the destination and vector search as one (fast, scalable) vehicle. The mechanics of the vehicle — embeddingsEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords., cosine similarity, nearest-neighbor search — are covered in the embeddings and vector search articles; I won’t re-derive them here.

How it actually works under the hood

Four moving parts, roughly in order:

1. Query understanding — intent classification (informational, navigational, transactional, commercial), entity extraction, and synonym/concept expansion. This is RankBrain and BERT territory.
2. Entity recognition + the Knowledge Graph — identifying the real-world things a query and a document are about, and disambiguating them. About 40% of English words have multiple meanings; context resolves which one you mean.
3. Embeddings and semantic similarity — encoding meaning as vectors so “fix a leaky faucet” and “repairing a dripping tap” land close together (~0.89 similarity despite barely sharing a word). Deep dive in embeddings.
4. Passage rankingPassage ranking is a Google AI system that scores individual sections ('passages') of a page so a single page can earn multiple relevance scores for different queries. Google still indexes whole pages — only the ranking changed. and neural re-ranking — since 2020, individual passages of a page can rank for a query even when the whole page isn’t perfectly targeted, and a neural re-ranker reorders the keyword-retrieved set by semantic fit. This is why each section needs to stand on its own.

The LSI keyword myth

This one matters because it drives a lot of bad advice. “LSI keywords” (Latent Semantic IndexingStoring a crawled page in the search index so it can appear in results. Crawled is not the same as indexed — Google selects what to keep, and indexing isn't guaranteed.) is a 1988 information-retrieval technique that Google has never confirmed using as a ranking input. John Mueller put it flatly: “There’s no such thing as LSI keywords — anyone who’s telling you otherwise is mistaken, sorry.” What Google actually uses is far more sophisticated — neural matching, BERT, word embeddings, entity recognition. So when a tool hands you a list of “LSI keywords,” what’s useful about it isn’t the LSI part; it’s that those terms reflect the vocabulary of the topic. Cover the topic naturally and you get that for free.

What semantic search means for SEO

Every major semantic update has pushed in the same direction, which makes the playbook unusually stable:

• Topic coverage beats keyword density. Google judges whether a page covers a topic thoroughly, not whether it hits a keyword n times. Deep coverage ranks for dozens of related queries you never targeted individually.
• Entity optimization. Name and describe your entities clearly; use structured data (sameAs, @id) to disambiguate them against Wikipedia/Wikidata. This is the entity SEOEntity SEO is the practice of helping search engines and AI systems clearly identify, classify, and trust the entities you represent — your brand, your people, your products — rather than just matching keyword strings. The goal is to be an unambiguous, well-corroborated entity in machine knowledge systems so AI can cite you with confidence. discipline.
• Intent alignment is non-negotiable. Google classifies query intent and filters by it. A page that answers a different intent than the query won’t rank no matter how well the keywords match.
• Write naturally. With BERT reading context, prepositions and sentence structure carry meaning. Gary Illyes’ advice on RankBrain still holds: “If you try to write like a machine then RankBrain will just get confused and probably just pushes you back.”
• Synonyms are handled for you. You don’t need every variation; covering the topic’s natural vocabulary signals depth without stuffing.
• Passage-level quality. Each H2/section should stand alone as a clean, self-contained answer — that’s what passage rankingPassage ranking is a Google AI system that scores individual sections ('passages') of a page so a single page can earn multiple relevance scores for different queries. Google still indexes whole pages — only the ranking changed. and AI OverviewsAI Overviews are the AI-generated summary box Google shows above or within its regular search results, written by Gemini models from pages retrieved out of Google's normal Search index. It's a Search feature, not a separate platform or index. retrieve.

When semantic SEO matters less

Honesty check: for a single-service local business or a thin site, heavy entity and topical-authority work may not pay off. The ROI shows up when you’re competing on informational depth across a topic. As Sally Mills put it, “If you do SEO properly, you’re automatically doing semantic SEO. It’s just that most people aren’t doing it properly.” And Google won’t go purely semantic anytime soon — full semantic retrieval is expensive, exact-match is still common user behavior, and purely semantic results remain unreliable. Keyword retrieval and semantic understanding coexist.

How AI search builds on this

AI Overviews, AI Mode, and AI assistants are semantic search plus generation. They retrieve passages by meaning (usually dense retrieval — see RAG and vector search), then an LLM writes the answer. Bing’s framing of the shift is sharp: groundingGrounding is anchoring an AI model's answer to source documents it retrieves at the moment you ask — not to the patterns frozen into its weights during training. Retrieval-Augmented Generation (RAG) is the most common way to do it. indexing, in their words, “is being built to help AI systems decide what to say.” The practical consequence: the same things that make a passage rank well — clear entities, self-contained sections, topical depth — are what make it likely to be cited in an AI answer. There’s no separate trick.

AI summary

A condensed take on the Advanced version:

• Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. = retrieval by meaning, not exact keyword match. That distinction is the whole point. “Fix a leaky faucet” and “repairing a dripping tap” should return the same results despite sharing no words.
• It augments keyword search, it doesn’t replace it. BM25-style retrieval still runs first at scale (speed + recall); neural systems re-rank and add concept-matched documents. DOJ testimony confirmed Google’s embeddingEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. layer (RankEmbed) adds documents to traditional retrieval.
• Google built it in layers: Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. (2012, “things not strings”) → Hummingbird (2013, whole-query meaning, 90% of searches) → RankBrain (2015, novel queries) → neural matching (2018, concept-level “super synonyms,” 30% of queries) → BERT (2019, contextual word meaning, 1-in-10 queries) → MUM (2021, multimodal, 75 languages, never the general ranking engine).
• Semantic search ≠ vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds.. Semantic search is the goal; vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one implementation (others: query expansion, synonym rules, Knowledge Graph lookups).
• “LSI keywords” are a myth — John Mueller said so directly. Google uses neural matching, BERT, and embeddingsEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. instead.
• SEO playbook (unchanged across a decade): topic coverage over keyword density, clear entities + structured dataStructured data is a standardized way of labeling page content (using the schema.org vocabulary in JSON-LD, Microdata, or RDFa) so search engines can understand its meaning. It's not a direct ranking factor — its value is rich results and entity understanding., intent alignment, natural-language writing, passage-level quality. Keyword research still matters; keyword stuffing doesn’t.
• AI searchAI search uses large language models and retrieval-augmented generation (RAG) to synthesize an answer from multiple sources rather than returning a ranked list of links. Examples include Google AI Overviews, ChatGPT Search, and Perplexity. = semantic retrieval + generation. What ranks well (clear entities, self-contained passages, depth) is what gets cited.

Official documentation

Primary-source documentation and announcements from Google and Microsoft.

Google

• A guide to Google Search ranking systems — official current descriptions of BERT, neural matching, RankBrain, MUM, and Passage RankingPassage ranking is a Google AI system that scores individual sections ('passages') of a page so a single page can earn multiple relevance scores for different queries. Google still indexes whole pages — only the ranking changed. (and the list of retired systems, including Hummingbird).
• Introducing the Knowledge Graph: things, not strings — the 2012 entity launch and the “things, not strings” framing.
• Understanding searches better than ever before (BERT) — Pandu Nayak’s 2019 BERT announcement, with the visa/esthetician examples.
• MUM: A new AI milestone for understanding information — the 2021 multimodal, multilingual model.
• How AI powers great search results — Google’s overview of how RankBrain, neural matching, BERT, and MUM fit together.

Microsoft / Bing

• The Science Behind Semantic Search (Azure AI) — “a Transformer-based semantic ranking engine that understands the meaning behind the text.”
• Semantic ranking in Azure AI Search — the BM25/RRF retrieval → transformer re-rankingReranking is the second stage of a retrieval pipeline: after a cheap, broad first pass pulls a candidate set of documents or passages, a slower, more precise model re-scores and reorders that shortlist by true relevance before the results are served or handed to an LLM. pattern, spelled out.
• Towards More Intelligent Search: Deep Learning for Query Semantics — rare technical depth on Bing’s pre-BERT neural ranking (GloVe vectors, CNN + cosine similarity).
• Introducing Deep Search — one of the earliest public descriptions of query fan-outQuery fan-out is the technique where an AI search system breaks a single user question into multiple related sub-queries, runs those searches concurrently, and synthesizes the retrieved results into one answer. Google confirms AI Overviews and AI Mode 'may use a query fan-out technique' issuing multiple related searches across subtopics. at production scale.

Quotes from the source

On-the-record statements from Google and Microsoft reps. Where a deep link is available it jumps to the quoted passage on the source page.

Google — the semantic shift

• “Things, not strings.” — Amit Singhal, introducing the Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself., 2012. Jump to quote

Google — BERT (Pandu Nayak, 2019)

• “BERT models can therefore consider the full context of a word by looking at the words that come before and after it — particularly useful for understanding the intent behind search queries.”
• “[The] biggest leap forward in the past five years, and one of the biggest leaps forward in the history of Search.”
• “Language understanding remains an ongoing challenge, and it keeps us motivated to continue to improve Search.” Jump to quote

Danny Sullivan, Google Search Liaison

• On neural matching (2018): “Last few months, Google has been using neural matching — AI method to better connect words to concepts. Super synonyms, in a way, and impacting 30% of queries.”
• “RankBrain helps Google better relate pages to concepts. Neural matching helps Google better relate words to searches. It’s like a super synonym system.”
• On optimizing for BERT (2019): “There’s nothing to optimize for with BERT, nor anything for a site owner to be ‘concerned’ about. The fundamentals of us seeking to reward great content remain unchanged.”

Gary Illyes, Google

• On writing for RankBrain (Big Digital Adelaide, 2016): “Optimizing for RankBrain is actually super easy… write in natural language. Try to write content that sounds human. If you try to write like a machine then RankBrain will just get confused and probably just pushes you back.”

John Mueller, Google

• On the LSI myth (Twitter, July 30, 2019): “There’s no such thing as LSI keywords — anyone who’s telling you otherwise is mistaken, sorry.”

Greg Corrado, Google (on RankBrain, via Bloomberg, 2015)

• “RankBrain uses artificial intelligence to embed vast amounts of written language into mathematical entities — called vectors — that the computer can understand. If RankBrain sees a word or phrase it isn’t familiar with, the machine can make a guess as to what words or phrases might have a similar meaning and filter the result accordingly.”

Pandu Nayak, Google (DOJ antitrust testimony, 2023)

• “RankEmbed identifies a few more documents to add to those identified by the traditional retrieval.” (Confirms that Google’s semantic embeddingEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. layer augments classical keyword retrieval rather than replacing it.)

Microsoft — Azure AI / Bing

• “Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. is moving beyond keyword-based ranking to a Transformer-based semantic ranking engine that understands the meaning behind the text.” — Microsoft Research, 2021.

Google’s semantic milestones — cheat sheet

The layered stack, in order. Each solved a different problem; none replaced the one before it.

Quick distinctions to keep straight

• RankBrain vs. BERT — RankBrain maps unknown queries to known concepts; BERT understands the contextual meaning of words within a query sentence.
• Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. vs. vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. — semantic search is the goal; vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one implementation (others: query expansion, synonym rules, Knowledge Graph).
• Semantic SEO — topic coverage, entity relationships, intent matching. Not synonym stuffing, and definitely not “LSI keywords” (a myth — see the article).
• Keyword search isn’t dead — BM25-style retrieval still runs first; semantic systems re-rank and add concept-matched documents on top.

The mental models

1. Goal vs. implementation. Semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. is the destination (retrieve by meaning). Vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one vehicle (embeddingsEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. + nearest-neighbor). You can also walk there — query expansion, synonym rules, entity lookups. Don’t conflate the destination with one route.

2. The layered stack, not a switch. Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. (entities) + RankBrain (unknown queries) + neural matching (concept synonyms) + BERT (word context) + MUM (multimodal). They stack and cooperate; no update threw out the previous one. When you reason about “how Google understands this query,” ask which layer is doing the work.

3. Retrieval is two-stage. Stage 1: fast, keyword-based, high-recall (BM25 over an inverted indexStoring a crawled page in the search index so it can appear in results. Crawled is not the same as indexed — Google selects what to keep, and indexing isn't guaranteed.). Stage 2: neural re-rankingReranking is the second stage of a retrieval pipeline: after a cheap, broad first pass pulls a candidate set of documents or passages, a slower, more precise model re-scores and reorders that shortlist by true relevance before the results are served or handed to an LLM. + concept-matched additions. Semantic search is mostly stage 2 — it augments stage 1, it doesn’t delete it.

4. The optimization invariant. Every semantic update points the same way: natural language, topical depth, clear entities, intent alignment. If a tactic only makes sense to a keyword-counting engine (stuffing, exact-match obsession, “LSI keywords”), it’s optimizing for a machine that no longer exists.

5. The “what gets cited” rule for AI searchAI search uses large language models and retrieval-augmented generation (RAG) to synthesize an answer from multiple sources rather than returning a ranked list of links. Examples include Google AI Overviews, ChatGPT Search, and Perplexity.. AI answers = semantic retrieval + generation. What ranks a passage (clear entities, self-contained sections, depth) is what gets it retrieved and cited. There’s no separate AI-search trick — it’s the same passage-level quality.

Semantic-search mistakes

Building pages around lists of “LSI keywords”

LSI keyword advice mislabels how modern retrieval works. Cover the subject naturally, name real entities and relationships, and answer the user’s intent instead of adding a mechanically generated synonym list.

Treating semantic search and vector search as synonyms

Semantic retrieval is the goal of matching meaning; vectors are one method that can support it. Keep the distinction when evaluating a system or choosing an audit.

Repeating the head term instead of resolving ambiguity

More repetition does not clarify which entity or intent a page serves. Use explicit names, attributes, context, and connected subtopics so meaning survives beyond a single keyword string.

Test yourself: Semantic search

Resources worth your time

My related reviews

• Semantic SEO (Ahrefs) — the advanced practitioner guide (I’m a reviewer on this one), covering the EAV model and why Google won’t go purely semantic.

On this site

• Entity SEOEntity SEO is the practice of helping search engines and AI systems clearly identify, classify, and trust the entities you represent — your brand, your people, your products — rather than just matching keyword strings. The goal is to be an unambiguous, well-corroborated entity in machine knowledge systems so AI can cite you with confidence. — the practical discipline of naming, describing, and disambiguating entities (the Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. side of semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it.).
• EmbeddingsEmbeddings are dense numerical vectors — lists of floating-point numbers — that represent the meaning of text in a high-dimensional space. Semantically similar content lands close together, so search and AI systems can match by meaning, not just keywords. and vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. — the technical mechanism that makes meaning-based similarity work.
• RAGRAG is the retrieve-then-generate pattern behind AI search: the system retrieves relevant passages from an external index at query time, injects them into the model's context, and generates an answer grounded in those sources — without changing the model's weights. — how AI searchAI search uses large language models and retrieval-augmented generation (RAG) to synthesize an answer from multiple sources rather than returning a ranked list of links. Examples include Google AI Overviews, ChatGPT Search, and Perplexity. retrieves passages and grounds generated answers.

From others

• Semantic Search — Mateusz Makosiewicz’s Ahrefs guide to meaning-based retrieval, entities, and content.
• Google’s Knowledge Graph — Despina Gavoyannis and Michal Pecánek’s Ahrefs guide to entity data and SEO.
• RankBrain glossary and Hummingbird glossary (Ahrefs) — quick reference entries from the Ahrefs editorial team.
• Google’s Search ranking systems guide — the authoritative list of what’s live and what’s retired.
• SEO by the Sea — Hummingbird retrospective — detailed history with Singhal context.
• Google Hummingbird (Search Engine Land) — Danny Sullivan’s original 2013 announcement report with Singhal quotes; primary source for “90% of searches” and full-phrase meaning.
• Meet RankBrain, Google’s Artificial Intelligence Search Algorithm (Search Engine Land) — the original 2015 report breaking RankBrain, with Greg Corrado’s verbatim quotes on vectors and unknown queries.
• Google Neural Matching (Search Engine Journal) — covers the 2018 neural matching launch, Danny Sullivan’s “super synonyms” tweet, and the distinction from RankBrain.
• FAQ: All About the BERT Algorithm in Google Search (Search Engine Land) — comprehensive Q&A including Danny Sullivan’s “nothing to optimize for” guidance.
• Google Turning Its Lucrative Web Search Over to AI Machines (Bloomberg) — the original RankBrain disclosure; Greg Corrado confirms it as “the third-most important signal.”
• The Science Behind Semantic Search: How AI from Bing Is Powering Azure Cognitive Search (Microsoft Research) — Bing’s BM25 → transformer re-rankingReranking is the second stage of a retrieval pipeline: after a cheap, broad first pass pulls a candidate set of documents or passages, a slower, more precise model re-scores and reorders that shortlist by true relevance before the results are served or handed to an LLM. pipeline explained; includes the 2% / 4.5% CTR lift data from Microsoft Docs testing.

Videos

• Google Search Central (YouTube) — the How Google Search WorksSearch works in three stages — crawling, indexing, and serving (ranking). A page has to clear each one to appear in results: getting crawled doesn't mean you're indexed, and getting indexed doesn't mean you rank. series, including the explainers on query understanding and the systems behind it. Channel

Stats worth citing

• ~40% of English words have multiple meanings — which is why context (location, history, surrounding words) is what semantic searchSemantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it. uses to disambiguate “apple” or “jaguar.” Source
• ~0.89 vector similarity between “how to fix a leaky faucet” and “repairing a dripping tap” — despite sharing almost no words. The concrete face of meaning-based matching. Source
• Neural matching affects ~30% of queries (Danny Sullivan, 2018) — the scope of concept-level “super synonym” matching.
• BERT affected 1 in 10 US English queries at launch (Pandu Nayak, 2019) and now plays a role in nearly every English query. Source
• The Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. holds ~1.6 trillion facts about ~54 billion entities today (up from 500M entities at 2012 launch) — the scale of Google’s entity backbone. Source

Semantic Search

Semantic search is meaning-based retrieval — matching what a user means, not just the words they typed. Search engines detect entities, expand synonyms, infer intent, and rank by conceptual relevance, which is why keyword stuffing lost its power and topical depth gained it.

Related: Entity SEO, Embeddings, Vector Search, Retrieval-Augmented Generation (RAG)

Semantic Search

Semantic search is the approach to information retrieval that focuses on the meaning of a query and the meaning of content — rather than counting exact keyword matches. A semantic search engine asks two questions: “what does the user want?” and “what does this document actually say?” — then matches intent to content at a conceptual level. It covers query understanding (intent detection, entity extraction, synonym expansion), document understanding (topic modeling, entity recognition, passage-level analysis), and relevance ranking that rewards topical depth and contextual fit over keyword density.

Google’s signature framing for the shift is Amit Singhal’s “things, not strings” — the move from matching text to understanding real-world entities and their relationships, which the Knowledge GraphThe Knowledge Graph is Google's database of entities — people, places, organizations, and things — and the factual relationships between them. It's separate from any single website's structured data: your schema markup is one of many possible inputs to the graph, not the graph itself. made concrete in 2012. The semantic stack is layered, not a single switch: the Knowledge Graph handles entities, RankBrain (2015) interprets never-before-seen queries, Neural Matching (2018) connects concepts between query and document, BERT (2019) reads the contextual meaning of words within a sentence, and MUM (2021) adds multilingual, multimodal reasoning. They work together.

A key distinction: semantic search is the goal (retrieve by meaning); vector searchVector search finds content by comparing the meaning of a query against stored content as numerical vectors, retrieving the closest ones in a high-dimensional embedding space. At scale it uses approximate nearest neighbor (ANN) algorithms — not exact comparison — to search billions of vectors in milliseconds. is one implementation of it (represent items as dense vectors and find nearest neighbors). Semantic search can also be achieved through query expansion, synonym rules, knowledge-graph lookups, and entity recognition. For SEO, the practical upshot is consistent across every update: write naturally, cover topics thoroughly, name entities clearly, and match intent — not stuff keywords or chase synonyms.

Related: Entity SEO, Embeddings, Vector Search, Retrieval-Augmented Generation (RAG)

Changelog