Google has made great strides in understanding user intent, but Director & Product Manager Elizabeth Tucker reveals that two types of queries continue to pose challenges.
In a recent episode of Google’s Search Off The Record podcast, Tucker discussed some persistent pain points in the company’s efforts to match users with the information they seek.
Among the top challenges were searches containing the word “not” and queries involving prepositions, according to Tucker.
“Prepositions, in general, are another hard one. And one of the really big, exciting breakthroughs was the BERT paper and transformer-based machine learning models when we started to be able to get some of these complicated linguistic issues right in searches.”
BERT, or Bidirectional Encoder Representations from Transformers, is a neural network-based technique for natural language processing that Google began using in search in 2019.
This technology helps Google understand the nuances and context of words in searches rather than simply treating queries as separate terms.
‘Not’ There Yet
Despite the advancements in BERT and similar technologies, Tucker admits that Google’s ability to interpret complex queries is still a work in progress.
Searches with the word “not” remain a challenge for the search engine, as Tucker explains:
“It’s really hard to know when ‘not’ means that you don’t want the word there or when it has a different kind of semantic meaning.”
For example, a search like “shoes not made in China” could be interpreted in multiple ways by Google’s algorithms.
This ambiguity presents a challenge for websites aiming to rank for such queries, as it may be difficult for Google to match the searcher’s intent with the content on a page.
The Preposition Problem
Another area where Google’s algorithms can struggle is with prepositions, which indicate the relationships between words in a sentence.
Queries like “restaurants with outdoor seating” or “hotels near the beach” rely on prepositions to convey crucial information about the user’s needs.
For SEO professionals, optimizing for queries with prepositions may require extra finesse to ensure the content effectively communicates the relationships between keywords.
The Long Tail Challenge
Google’s difficulties with complex queries are especially relevant to long-tail searches, which comprise a significant portion of all search traffic.
Although long-tail keywords offer SEO opportunities due to their specificity and user intent, Google’s challenges in understanding these queries can make it harder for websites to rank for them.
The Road Ahead
Tucker mentions that Google is actively improving its handling of these linguistically tricky queries, but a complete solution is still on the horizon.
“I would not say this is a solved problem. We’re still working on it.”
In the meantime, users may need to rephrase their searches or try different query structures to find the information they seek – a frustrating reality in an age when many expect Google to intuitively understand their needs.
Why SEJ Cares
Despite advancements like BERT, Google’s struggles with “not” queries and prepositions highlight the ongoing need for improvement in understanding user intent.
As Google invests in natural language processing and AI-driven technologies, the impact of these challenges on the search experience remains uncertain.
What It Means For SEO
So how can SEO professionals and website owners respond to this information? Here are some key considerations:
- Emphasize clarity and specificity in your content to help Google understand and rank your pages more effectively.
- Utilize structured data and technical SEO best practices to assist search engines in parsing your content.
- Monitor your search traffic and rankings for complex queries, and be prepared to adjust your strategy as needed.
- Stay informed about Google’s advancements in natural language understanding and be ready to adapt to new algorithms and technologies.
Listen to the full podcast episode below: