Two parts: query understanding (language, synonyms, entities, query rewriting, query fan-out) by John Mueller, then retrieval from the index (posting lists, language, country and quality signals) by Gary Illyes. Speakers from on-stage references: a later talk called the first part John's talk, and the first part ended by handing over to Gary.
Said on stage 71
Google's query understanding talk set out to show how the changes Google makes to users' queries relate to what a website can provide.
Speaker John MuellerEvidence transcript
A Google speaker said that a messy query, made of a hotel location copied from a website plus a question about Italian food, was figured out by Google's systems, which came up with answers for it.
Speaker John MuellerEvidence transcript
Google placed query understanding in the traditional part of Search, the part where answers are looked up in an index and then presented and ranked.
Speaker John MuellerEvidence transcript
- Extended by D3-C304 Day 3: Which kinds of results Google shows for a query is decided by query understanding, which tries to predict the…
Google said it has no name for traditional, non-AI Search, only for its Search generative AI features, and that the two play together but are easier to understand separately.
Speaker John MuellerEvidence transcript
Google's first step in understanding almost any query is to detect its language, which tells Google roughly what content the user wants: a query in German suggests German content, a query in English English content.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-07glossary term Query understanding
- Extends D2-C654 Day 2: In ranking, country and language signals help Google serve users the right content for their country and…
Query language detection works poorly when someone searches only for a brand name, such as Facebook or Google, because the query does not show which language the user wants results in.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-03
- Extends D1-C215 Day 1: Serving starts with interpreting the query, which includes cleaning it up, detecting its language and…
For brand-only queries Google falls back on other information, such as the user's location and browser settings, to work out the language of the results.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-03
Because a brand-only query does not reveal the user's language, Google sometimes struggles to show the right language version of a page for brand searches.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-03
Google named Thai as a language that makes query understanding more complex because it does not separate words with spaces; the speaker added, hedging with 'apparently', that Thai uses spaces to separate sentences.
Speaker John MuellerEvidence transcript
- Extends D2-C320 Day 2: Text in languages written without spaces, such as Thai and Chinese, would end up in the index as long strings…
After detecting the query language and separating the words, Google removes words it thinks matter little to the query, such as 'a' and 'of', known as stop words.
Speaker John MuellerEvidence transcript
Used byglossary terms Query understanding, Stop words
Google's query processing deliberately mirrors indexing: a query is transformed into something that can be matched against the index, and stop word removal is part of that transformation.
Speaker John MuellerEvidence transcript
- Extends D2-C321 Day 2: For languages written without spaces, such as Thai and Chinese, Google uses exactly the same word…
- Extends D2-C737 Day 2: A search query is broken into words with the same segmenter or tokenizer that Google used to build the index.
For some searches the stop words are important, and Google then tries to recognise the whole phrase, stop words included, as an entity; in indexing, such words are indexed together.
Speaker John MuellerEvidence transcript
Used byglossary term Stop words
Google said the difference between words and entities can be seen in Google Trends, where a term can be searched as words or as an entity (Trends calls these a search term and a topic).
Speaker John MuellerEvidence transcript
- Extends D2-C761 Day 2: The Google Trends Explore page, which Google called the heart of Trends, shows search interest in a query or…
When a query names an entity, Google treats it as a request for that entity rather than as a collection of separate words.
Speaker John MuellerEvidence transcript
Used byglossary term Query understanding
In ranking, Google can match a query's words or its entity, and, the speaker said with a 'probably', mixes both to some degree.
Speaker John MuellerEvidence transcript
Google expands queries with synonyms in traditional Search; the speaker compared this to query fan-out but said it is part of traditional Search, not of the AI features.
Speaker John MuellerEvidence transcript
In Google's example, the query word 'photograph' could be expanded to 'image', 'picture' or 'photo', but one German candidate had to be dropped because the similar German word means 'photographer', so expansions are language-specific.
Speaker John MuellerEvidence transcript
According to Google's ranking teams, the synonym system is one of the most important parts of how Google handles a query.
“they say that the synonym system is one of the most important parts”
Speaker John MuellerEvidence transcript
Synonyms matter because users often phrase a query differently from the way content is indexed; synonym expansion makes the words Google looks up findable in its index.
Speaker John MuellerEvidence transcript
For technical terms, Google's synonym swapping can return either a technical page or a simplified page for the same query.
Speaker John MuellerEvidence transcript
Site owners do not need to list all synonyms of a term on a page, because Google already knows the synonyms and looks for them on pages too.
“you don't have to do that SEO meme of, like, list all the synonyms on your page”
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
Google adds alternative words to a query automatically, which the speaker compared to a user joining words with the OR search operator.
Speaker John MuellerEvidence transcript
Used byglossary term Synonyms and siblings
Google suggested a test: a search that lists a term's synonyms joined with OR will probably return results very similar to the plain query, because Google adds the synonyms itself (part of the sentence is unclear in the recording).
Speaker John MuellerEvidence transcript
Googlers write queries in brackets, for example [spicy cheese store near me], so when reporting a search problem to a Googler, putting the query in brackets shows that it is a query someone searched.
Speaker John MuellerEvidence transcript
Google rewrites pretty much every query, through synonym expansion and in other ways, to understand better what the query means.
“pretty much all queries are rewritten”
Speaker John MuellerEvidence transcript
Used byglossary term Query understanding
Internally, a short query can turn into a much longer rewritten query, because Google adds entities, synonyms and other information before looking it up.
Speaker John MuellerEvidence transcript
In Google's rewrite example, [fried chicken place in Barcelona] keeps 'fried' and 'chicken' as two words, may add an entity for fried chicken, and replaces 'place' with alternatives such as 'area', 'location' or 'restaurant'.
Speaker John MuellerEvidence transcript
Some alternatives in a rewritten query make no sense, such as 'fried chicken area in Barcelona', which is harmless because few indexed pages match them.
Speaker John MuellerEvidence transcript
In a rewritten query, a place name such as Barcelona can stay a word or be swapped for an entity, possibly a more specific location.
Speaker John MuellerEvidence transcript
For a query containing 'near me', Google understands that the user wants results near their location, not pages containing the words 'near me', and rewrites the query accordingly.
Speaker John MuellerEvidence transcript
Some synonyms are contextual and depend on the rest of the query: 'GM' probably means General Motors in [GM car], general manager in [GM restaurants] and genetically modified in [GM barley].
Speaker John MuellerEvidence transcript
Google builds its synonyms as automatically as possible, behind the scenes, rather than having linguists catalogue every language and all possible synonyms.
Speaker John MuellerEvidence transcript
Google's synonyms need not be synonyms linguistically: words people use interchangeably are treated as synonyms, because the aim is to find the right content in the index.
“we don't need to be technically accurate”
Speaker John MuellerEvidence transcript
Used byglossary term Synonyms and siblings
When Google highlights a word in its results that looks like the wrong synonym, the reason is probably that many people use the two words interchangeably.
Speaker John MuellerEvidence transcript
Besides synonyms, Google detects 'siblings', words in the same category that are related but not interchangeable, such as Canon and Nikon.
Speaker John MuellerEvidence transcript
Used byglossary term Synonyms and siblings
Because Canon and Nikon are siblings rather than synonyms, a search for [Canon camera] should not show Nikon cameras.
Speaker John MuellerEvidence transcript
Used byglossary term Synonyms and siblings
Google learns synonyms and siblings from search behaviour: words people search with in the same way become synonyms, while frequent comparison queries mark words as not interchangeable (the end of the sentence is unclear in the recording).
Speaker John MuellerEvidence transcript
Google does not prefer English words on pages in other languages; the idea that Google, as an American company, wants to see everything in English is wrong.
Speaker John MuellerEvidence transcript
Where Google recognises an English term and its local-language equivalent as synonyms, a page does not need to contain both.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
To check whether Google treats two terms as the same, search for each: [Iberico ham] and [jamón ibérico] both brought up the same entity, so Google understands them as the same thing.
Speaker John MuellerEvidence transcript
When Google already matches a term's variants, there is no need to add them to pages artificially; mention another name only where visitors might not understand otherwise.
“I wouldn't artificially just stuff those variations in there.”
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
At the time of the talk, a search for [Spanish cured ham] brought up mainly a Wikipedia page, showing that Google does not automatically equate that phrase with Iberico ham.
Speaker John MuellerEvidence transcript
When Google does not treat a phrase as a synonym, such as 'Spanish cured ham' for Iberico ham, a page that wants to cover that phrase should use it in its text.
Speaker John MuellerEvidence transcript
Google generally treats spellings with and without diacritics as synonyms behind the scenes, for example a German 'ü' written as 'ü', as 'ue' or left out.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
- Extends D2-C600 Day 2: Google usually understands a query word whether it is written with or without diacritics (accents).
Google sometimes gets diacritic variants wrong, so it is worth searching to see whether Google understands a variant; if it does, pick one spelling and use it.
Speaker John MuellerEvidence transcript
Google's recommendation for diacritics, non-English words, product names and spelling variants is to focus first on what users actually search for.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
Users expect content written the way they search: in some languages they search in Latin characters, in others in the local script, and Hindi users, for example, search both in Hindi and in Latin letters.
Speaker John MuellerEvidence transcript
Used byrequirement DEV-INT-11
- Extends D2-C599 Day 2: Google usually understands non-English words typed 'in English' (probably meaning romanised, Latin-letter…
Google said focusing on what users actually do makes more sense than trying to match what the search engine does.
Speaker John MuellerEvidence transcript
Spelling variants need no artificial focus: users are often fine finding one version of a word on one page and another version elsewhere.
Speaker John MuellerEvidence transcript
Google advised double-checking any word you are unsure about by searching for it on Google and looking at what comes up.
Speaker John MuellerEvidence transcript
Google's generative AI features in Search build on the traditional ways of searching, so query understanding also flows into AI Overviews and AI Mode.
Speaker John MuellerEvidence transcript
- Repeats D1-C051 Day 1: Three reasons were given: generative AI features are built directly on the core ranking systems, query…
In Google's AI features, the query and the search results are additionally sent to an LLM, which returns new queries for Google to run.
Speaker John MuellerEvidence transcript
Used byglossary term Query fan-out
- Repeats D1-C053 Day 1: Query fan-out means running several related searches at once to gather more results; a question about lawn…
Google treats fan-out queries generated by the LLM the same way as queries typed by users, so understanding how normal queries work explains fan-out queries too.
Speaker John MuellerEvidence transcript
- Extends D2-C727 Day 2: Google said that when AI Overviews or AI Mode run a query fan-out, the generated queries are sent to Google's…
- Extends D1-C172 Day 1: Google said the Gemini model lets Search understand the user's intent, and query fan-out then adds further…
Google said a short video showing how one query is expanded into several fan-out queries has been in its documentation for a while.
Speaker John MuellerEvidence transcript
Google tries to make fan-out queries distinct from each other for better coverage, avoiding asking the same question several times, which would return the same answers.
Speaker John MuellerEvidence transcript
- Extends D2-C729 Day 2: Google says query fan-out in AI Overviews and AI Mode issues related searches across subtopics and several…
- Extends D1-C225 Day 1: Google said query fan-out is nothing new: it fires, for example, ten different searches in the background…
Every fan-out query goes through Google's query understanding, including synonym expansion.
Speaker John MuellerEvidence transcript
Used byglossary term Query fan-out
Google said fan-out queries are not added to Search Console, because Google considers them part of its infrastructure.
“Fan-out queries are not added in Search Console, because they're basically a part of our infrastructure.”
Speaker John MuellerEvidence transcript
Used byrequirement DEV-AIF-03glossary term Query fan-out
- Extends D1-C124 Day 1: Google's launch post for the Generative AI performance reports in Search Console (3 June 2026; rolled out to…
Individual fan-out queries can be seen in some other places, such as Gemini, some search APIs and other LLM systems.
Speaker John MuellerEvidence transcript
Because every system runs fan-out differently, Google advised understanding that fan-out happens but not overfocusing on individual fan-out queries or on how to rank for them.
“I would not overfocus on which individual fan-out queries happen and how can I rank for those”
Speaker John MuellerEvidence transcript
Used byrequirement DEV-AIF-03
- Extends D1-C129 Day 1: Google's guide says creating separate content for every variation of how people might search, including…
- Repeated by D3-C704 Day 3: Google warned that shiny new things, such as trying to work out fan-out queries, distract from the real…
After query understanding and expansion, Google sends the queries to the index to look up pages, the retrieval step.
Speaker John MuellerEvidence transcript
Used byglossary term Retrieval
Google's index uses posting lists: for each word, a list of the URLs associated with that word.
Speaker Gary IllyesEvidence transcript
- Repeats D2-C733 Day 2: For most of the tokens Google finds on the web, though not every single one, the index keeps a posting list…
At retrieval, Google splits the query into words, applies query understanding and expansion, and matches the words and their expansions against the posting lists.
Speaker Gary IllyesEvidence transcript
Used byglossary term Retrieval
- Extends D2-C736 Day 2: In posting-list retrieval, the posting lists of the query's words are intersected, which yields an unranked…
- Extends D2-C738 Day 2: At retrieval, Google looks up the posting lists of the query words that are actually important rather than of…
For retrieval, Google uses signals attached individually to each document in the index.
Speaker Gary IllyesEvidence transcript
- Repeats D2-C722 Day 2: Each document in Google's index has pretty much all the signals calculated for it attached, for example…
The first condition for retrieving a document is that the query's words, or its concepts in the case of vectors or embeddings, are in the document or related to it.
Speaker Gary IllyesEvidence transcript
- Extends D2-C740 Day 2: Besides posting lists, Google can retrieve documents through vector embeddings: parts of documents are…
Because a query like [best fried chicken ever] can match millions of pages, Google already orders the candidates during retrieval, before ranking starts.
Speaker Gary IllyesEvidence transcript
To order candidates at retrieval, Google uses signals collected during indexing, and the first two are language and country.
Speaker Gary IllyesEvidence transcript
Used byrequirement DEV-INT-07glossary term Retrieval
- Extends D2-C722 Day 2: Each document in Google's index has pretty much all the signals calculated for it attached, for example…
- Extends D2-C649 Day 2: Country and language are among Google's most important signals and have been used since Google's early days.
At retrieval, Google tries to match results to the user's language wherever possible: someone searching in Spanish does not necessarily want results in Italian.
Speaker Gary IllyesEvidence transcript
Used byrequirement DEV-INT-07
- Extends D2-C654 Day 2: In ranking, country and language signals help Google serve users the right content for their country and…
Where Google cannot find results in the user's language, the speaker called the gap an opportunity for whoever targets those words.
Speaker Gary IllyesEvidence transcript
Country is the second retrieval signal: a user searching from Switzerland wants cheese from Switzerland, not from Germany, and a user in Spain is poorly served by results targeting a South American country.
Speaker Gary IllyesEvidence transcript
Used byrequirement DEV-INT-07
- Extends D2-C649 Day 2: Country and language are among Google's most important signals and have been used since Google's early days.
Google called quality the most important of the signals used to order candidates at retrieval: a URL of high quality is more likely to be retrieved from the index for specific queries.
“if the quality of a URL is high, then it's more likely to be retrieved from the index for specific queries.”
Speaker Gary IllyesEvidence transcript
Used byglossary term Retrieval
- Extends D2-C722 Day 2: Each document in Google's index has pretty much all the signals calculated for it attached, for example…
The same quality signal that Google uses at retrieval is also used in ranking when results are served.
Speaker Gary IllyesEvidence transcript
- Extended by D3-C131 Day 3: Google's quality talk said quality is one of the most important ranking signals, although Google uses…