Google’s John Mueller answered a question about how Google’s algorithm handles abbreviations. John answered the question in depth, explaining how these are essentially synonyms and that Google doesn’t do anything particularly special with abbreviations.
How Does Google Handle Abbreviations?
The person asking a question wanted to know how Google handled abbreviations such as “eg” which means ergo.
They related that they have a lot of these kinds of abbreviations on their site.
Google’s John Mueller answered:
“And the short answer is we don’t do anything special with those kinds of things.
We essentially treat them as tokens on a page.
And a token is essentially kind of like a word or a phrase on a page.
And we would probably recognize that there are known synonyms for some of these and understand that a little bit.
But we wouldn’t really do anything specific there in that we’d like have a glossary of what this abbreviation means and handle that in a specific way.
So that’s something where, especially when it comes to synonyms, our systems learn these over time.
And for the most part, we handle them when people search and not when we do the indexing.”
John Mueller next recommends watching a video of Google Search Engineer Paul Haahr speaking at a search conference that was published by Google Search central in which he talks about how search works, in which Paul discusses the use of synonyms for query expansion.
Mueller says:
“And in that video, he goes through some of the synonym challenges that we’ve run across in the past.
And I found that super interesting to look at and probably also gives you some ideas on how we might handle some of these kind of expansions when it comes to abbreviations.”
Mueller said that the video was from December 2019 or 2020 and published on Google Search Central’s YouTube channel.
And there is indeed a video from 2019 that was published in 2020 in which Paul Haahr talks about synonyms and query expansion.
Paul discusses the topic of query expansion and synonyms at the 1:30 minute mark:
Google Video of Paul Haahr Discussing Synonyms and Query Expansion
https://youtube.com/watch?v=DeW-9fhvkLM%3Fstart%3D91%26feature%3Doembed%26enablejsapi%3D1%26origin%3Dhttps%3A
“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 shows 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:
“So what is our synonym system?
It’s something that is there to bridge the gap between the user vocabulary and query vocabulary – or user vocabulary and document vocabulary.
That is, when we see a query, it often is written in a different language than the documents used.
And we’re trying to match those things.
The way this actually works is, it looks a lot like we add a bunch of terms with OR.
Who here in the audience has used the OR operator?
And the way our synonyms system works is effectively, we take a user query and we add a lot of OR terms to it.
And this is actually one of Google’s most important ranking components… that it’s sort of.. it’s something that we launched roughly 15-plus years ago, has improved a lot over the years.”
More Videos of Paul Haahr Discussing Synonyms and Query Expansion
There is another video of Paul Haahr speaking at SMX West in 2016 where he also speaks about query expansion and this also sheds some light on the topic.
