Google Knowledge Graph, Semantic Search and Language Handling

In Search Technology by MediaVision

The ultimate goal for any search engine is being able to provide users with the most relevant and topical results for search queries. When humans communicate there are obvious instances where the context of a query or question determines the answer that you receive.

Asking a friend about “the Olympic games” will probably be met with counter questions to put your query into context. Are you asking about the Olympic schedule, a specific country’s medal count or your favourite sports person and when he/she is competing?

This seemingly insignificant ability that humans have is impossible for a machine and this is what Google is trying to do with the Knowledge Graph and Semantic search. Google now has the ability to “ask questions” regarding your query and provides you with the options to further refine your results.

So How Does the Knowledge Graph work?

Google searches are essentially questions being asked in a shortened and truncated manner using keywords or key phrases. So when you ask the question “Olympic Games”, Google now has to determine what information it is that you are after and that’s where Semantic search comes in (referred to as Knowledge Graph by Google).

google-knowledge-graph

Where Does Google find all that Information and deliver it to searchers?

Google’s Knowledge Graph indexes universal definitions using every public database at its disposal. The result is an information index of 500 million people, places and things with 3.5 billion connections among them. The Knowledge graph effectively asks questions to clarify the context of your question and allows you to augment your query to find the exact information that you are looking for.

In order to provide you with even more accurate results, Google will also take your search profile and location into consideration.

Google continues to expand and tweak its language interpretation skills constantly. Another string of recent changes made to Google’s algorithm includes how synonyms are handled and further improves search results by ‘knowing’ what searchers are looking for. Below are the updates straight from Google’s inside Search Blog.

#81933. [project codename “Synonyms”] This launch improves use of query synonyms in ranking. Now we’re less likely to show documents where the synonym has a different meaning than the original search term.

gallium-2. [project codename “Synonyms”] This change improves synonyms inside concepts.

zinc-4. [project codename “Synonyms”] This change improves efficiency by not computing synonyms in certain cases.

#82460. [project codename “Snippets”] With this change we’re using synonyms to better generate accurate titles for web results.

#81977. [project codename “Synonyms”] This change updates our synonyms systems to make it less likely we’ll return adult content when users aren’t looking for it.

The ultimate goal is smart search that thinks like you do, takes your individual preferences and location into account and uses this data to provide you with the information you want and need instantly.

What are your thoughts on the Semantic Web? Do you find the Knowledge Graph helpful in finding the information that you require?

#81933. [project codename “Synonyms”] This launch improves use of query synonyms in ranking. Now we’re less likely to show documents where the synonym has a different meaning than the original search term.

gallium-2. [project codename “Synonyms”] This change improves synonyms inside concepts.

zinc-4. [project codename “Synonyms”] This change improves efficiency by not computing synonyms in certain cases.

#82460. [project codename “Snippets”] With this change we’re using synonyms to better generate accurate titles for web results.

#81977. [project codename “Synonyms”] This change updates our synonyms systems to make it less likely we’ll return adult content when users aren’t looking for it.

The ultimate goal is smart search that thinks like you do, takes your individual preferences and location into account and uses this information to provide you with the information you want and need instantly.

Do you find the Knowledge Graph helpful in finding the information that you require? What are your thoughts on its influence on SEO & PPC marketing?

About the Author

MediaVision

Share