Google’s John Mueller answers a question about how Google’s algorithm handles abbreviations. John answers the question in depth, explaining why these are essentially synonyms, and Google doesn’t do anything special with abbreviations.
How does Google handle abbreviations?
The person asking the question wants to know how Google handles acronyms like “eg”, which means ergo.
They say they have a lot of these acronyms on their website.
Google’s John Mueller replied:
“In short, we don’t do anything special about this type of thing.
We basically think of them as markup on the page.
Tokens are essentially like words or phrases on a page.
We may recognize that some of them have known synonyms and understand a little.
But we’re not going to do anything specific there, because we want to have a vocabulary of what this abbreviation means and handle it in a specific way.
So this is where our system learns these over time, especially when it comes to synonyms.
In most cases, we process people when they search, not when we index. “
Next, John Mueller suggests watching a video of Google Search Engineer Paul Haahr speaking at the Search Conference published by Google Search Central, where he talks about how search works, where Paul discusses query expansion using synonyms.
Mueller said:
“In that video, he goes through some of the synonym challenges we’ve had in the past.
And I find this looks very interesting and might also give you some ideas on how we might handle some of these extensions when it comes to abbreviations. “
Mueller said the video was from December 2019 or December 2020 and was posted on Google Search Central’s YouTube channel.
There is indeed a 2019 video released in 2020 where Paul Haahr talks about synonyms and query expansion.
Paul discusses the topic of query expansion and synonyms at 1:30 minutes:
Google Video of Paul Haahr Discussing Synonyms and Query Expansion
“So first I’m going to talk about something in one of our language understanding systems, which is the synonym system.”
The screen behind Paul displays the following text:
-
-
"User vocabulary ≠ Document vocabulary
-
System tries to bridge the gap by automatically adding alternative words
-
Similar to using OR, but usually less important than original terms
-
One of Google Search's most important components"
-
Paul Haahr explains the purpose of using synonyms:
“Then what is our synonym system?
It bridges the gap between user vocabulary and query vocabulary—or user vocabulary and document vocabulary.
That is, when we see a query, it is usually written in a different language than the document used.
We’re trying to match those things up.
The way this actually works is that it looks a lot like we added a bunch of terms with OR.
Has anyone in the audience used the OR operator?
The way our synonym system works is efficient, we take user queries and add a lot of OR terms.
It’s actually one of the most important ranking components of Google…it’s kind of…it’s something we launched about 15+ years ago and it’s improved a lot over the years. “
More videos of Paul Haahr discussing synonyms and query expansion
There’s also a video of Paul Haahr speaking at SMX West in 2016, where he also talks about query expansion, which sheds some light on this topic as well.
Paul discusses query expansion at 6:35 minutes in his presentation:
Watch Google engineer Paul Haahr discuss synonyms
This is not the video that John Mueller cited, but it also has interesting information.
Paul Hall explains:
“We do a query understanding part, we try to figure out what the query means, we do retrieval and scoring … and then we do some … tweaking.
So query understanding, the first question is, do we know any named entities in the query?
San Jose Convention Center, we know what that is. Matt Cutts, we know what that is.
So we label them.
Then, are there any useful synonyms?
GM in this case… does GM mean GM?
Does GM mean genetically modified?
My point is that context matters.
We look at the context of the entire query. “
google and acronym
Mueller appeared to be saying in his response that Google treats acronyms as synonyms. Therefore, when considering how Google understands the content of a page, abbreviations may be condensed into core meanings that can be considered synonyms.
Citation
How Google handles abbreviations
Watch John Mueller answer questions at 48:43
