Semantic search generates the most accurate search results possible based on the intent and context of user search queries. Unlike search methods that find literal matches to keywords, semantic search captures the meaning of search queries, helping end users and agents search for and locate content without prior knowledge of the exact keywords to use.
To understand how to tell if you have semantic search enabled and what the rollout plan looks like, see Understanding the semantic search rollout plan.
What is semantic search?
Semantic search uses artificial intelligence (AI) to process and understand the full meaning and intent of language used in search queries, similar to the way a human would. Specifically, machine learning (ML) and natural language processing (NLP) technologies work together in semantic search to help the search engine understand the user’s intent when they submit a search query. Understanding what the user is actually looking for, regardless of the keywords they use, helps the search engine return and rank the most relevant results.
For example, with semantic search, end users and agents can ask natural language questions instead of worrying about which keywords to use in order to get the best results. New agents can ask “how do I start using reports?” instead of trying to think of the best keywords to use or the sequence of keywords to use in their query. With semantic search, they can enter their question in the way that makes sense to them, and still see the most relevant articles at the top of the results.
How semantic search works
Help center search has historically relied on keyword matches between queries and content (for example, articles, community posts, or external records). However, it didn’t capture the “meaning,” or semantics, of a query. Semantic search, on the other hand, deploys natural language processing to understand the content of the search query and content. This helps the search engine identify complex patterns that are otherwise missed. In many cases, semantic search is able to find relevant results even when there is not a strong word overlap between the query and indexed content.
Relying on language models, semantic search can translate queries and help center articles into vectors (a numerical representation), and measure the distance between them. Articles closer in the vector space are considered to be more similar by the language model. The language model is trained on many text examples, and through these examples has learned how to accurately interpret the meaning of text accurately.
When semantic search is used, the search engine boosts the relevance of semantically better matches. This pushes the most relevant content, based on intent and context of the search query, to the top of the search results. Each time a search is performed, the search results are ranked not only based on keyword matches but also boosted by semantic matches.

How semantic search improves the search experience
Semantic search offers a more intuitive search experience that lets help center visitors search using their choice of terms. Since the incorporation of semantic search, an increase in search quality metrics such as mean reciprocal rank (MRR) and click through rate (CTR) has been observed. Specifically, MRR improves 7% on average with this first iteration of semantic search for English Zendesk help centers. More searches with clicks have also been observed.
By improving the search relevance, and ranking the most relevant results on top, semantic search produces the following help center improvements:
- End users can find the information they are looking for more easily, increasing the deflection power of your help center.
- Agents can be more efficient as they can find answers more quickly.
The degree of impact for semantic search depends on the search behavior of the user. Semantic search has particularly positive benefits for longer search queries, but still improves relevance for all types of search.
37 comments
Barbara Neu
Für mich funktioniert die semantische Suche gar nicht.
0
Sarah Karlsson
Will this also improve the search within Knowledge, for the agents?
0
Elaine
I sincerely apologize for the frustration and inconvenience caused by the delay in enabling Semantics search on your help center. We understand the importance of an efficient search system and the impact it has on your user experience.
I want to assure you that our team is actively working to address this issue and expedite the process of rolling out Semantics search to your account. We value your continued trust as our customer since 2017, and we are committed to delivering an enhanced search experience that meets your expectations.
I appreciate your patience during this time, and we are dedicated to resolving this matter promptly. If you have any further concerns or specific feedback, please feel free to reach out directly, and we'll do our best to assist you.
Thank you for your understanding, and we look forward to delivering an improved search functionality soon.
0
N Y
It seems we are waiting way too long for the Semantics search to be enabled on our help center. It is very frustrating because our current Zendesk search is so bad...our search analytics are not improving ad we were hoping this could help us. No one at Zendesk is giving a timeline for us...we have been their customers since 2017 now. This is causing us lots of search related issues and the default search itself should have been good. Our users now use Google search to get to our help center articles as that is much more accurate and better. It has been a year now since you rolled it out in the first place...what is taking you so long to roll it out to us???
-1
Web User 4104644a592d2860bc31fc87
Hi, is there any update on when this is planned for instant search? You mentioned Q3 being your next milestone.
I'm currently planning our help centre and am a bit cautious of relying too much on search, because instant search doesn't work very effectively (in my experience). This update would probably make a big difference.
0
Diogo Maciel
No momento ainda não temos uma previsão para essa expansão. Você pode seguir a nossa pagina de Updates para ser notificado sobre as atualizações que acontecem no sistema
https://support.zendesk.com/hc/en-us/categories/4405298749210-Zendesk-updates
Espero que isso ajude! Se houver duvidas, estou a disposiçao.
0
Sam Almeida
Qual a previsão para ficar disponível no Brasil?
1
Shawna James
1
N Y
We have been waiting all this year for our help center to get the semantics search...how long will it take Zendesk to roll it out to all? Our existing search is not that great and we have been hoping this would help us, Can we get an update as to what's going on?
1
Subin Binu
I believe early Q3 is past us. Is there a clear timeline on when to expect this feature?
0
Sign in to leave a comment.