After I wrote up the what is neural matching, I got to thinking and decided to email Google a bunch of questions, which I published at Search Engine Land as Danny Sullivan posted the answers on Twitter via the @searchliaison account.
I love how Google summed it up:
- RankBrain helps Google better relate pages to concepts.
- Neural matching helps Google better relate words to searches.
Google said the Neural matching helps them better relate words to searches. Neural matching is an artificial intelligence based system that Google began using in 2018 primarily to understand how words are related to concepts. Google said it is "like a super-synonym system." Synonyms are words that are closely related to other words, Google said. For example, neural matching helps us understand that a search for "why does my TV look strange" is related to the concept of "the soap opera effect." We can then return pages about the soap opera effect, even if the exact words aren't used, Google said.
Whereas with RankBrain, Google said RankBrain is an AI-based system Google began using in 2016 to understand how pages are related to concepts. It means we can better return relevant pages even if they don’t contain the exact words used in a search, by understanding the page is related to other words & concepts.
Here is a bit more:
That's fairly good. And rather than it being weird, it's desired. It's not uncommon that a page author writes something one way [adjust seat recline] and searcher looks another way [how do I tilt my chair!] -- so anything that bridges is good.
— Danny Sullivan (@dannysullivan) March 21, 2019
Does RankBrain and Neural matching work together? Kind of:
I saw "kind of" because we already have (and long have had) synonym systems. These go beyond those and do things in different ways, too. But it's an easy way (hopefully) to understand them.
— Danny Sullivan (@dannysullivan) March 21, 2019
Here are the original tweets from Google:
RankBrain is an AI-based system Google began using in 2016 to understand how pages are related to concepts. It means we can better return relevant pages even if they don’t contain the exact words used in a search, by understanding the page is related to other words & concepts...
— Google SearchLiaison (@searchliaison) March 21, 2019
For example, neural matching helps us understand that a search for "why does my TV look strange" is related to the concept of "the soap opera effect." We can then return pages about the soap opera effect, even if the exact words aren't used...
— Google SearchLiaison (@searchliaison) March 21, 2019
In summary:
— Google SearchLiaison (@searchliaison) March 21, 2019
-- RankBrain helps Google better relate pages to concepts
-- Neural matching helps Google better relate words to searches.
And there's nothing special searchers or webmasters need to do. These are part of our core systems designed to naturally increase understanding.
So no, no real way to "optimize" for it like for RankBrain.
Forum discussion at Twitter.
