domenica 20 marzo 2022

How Google Ranks Pages With Abbreviations Via @sejournal, @martinibuster

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 video marketing 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 “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. Paul discusses Query Expansion at the 6:35 minute mark in the presentation: Watch Google Engineer Paul Haahr Discuss Synonyms This is not the video John Mueller was referencing but it also has interesting information. Paul Haahr explains: “We do a query understanding part where we try to figure out what the query means, we do retrieval and scoring… and then we do some …adjustments.
So Query Understanding, first question is, do we know any named entities in the query?
The San Jose Convention Center, we know what that is. Matt Cutts, we know what that is.
And so we label those.
And then, are there useful synonyms?
Does General Motors in this context… does GM mean General Motors?
Does GM mean mean genetically modified?
And my point there is just that context matters.
We look at the whole query for context.” Google and Abbreviations
What Mueller seems to be saying in his response is that Google sees abbreviations as synonyms. So when thinking about how Google might understand a page of content, an abbreviation may be condensed to a core meaning which could be seen as a synonym.
Citation
How Google Handles Abbreviations Watch John Mueller answer the question at the 48:43 minute mark

Nessun commento: