Fact Extraction and Knowledge Graphs

Techniques and approaches that search engines might use to do fact extraction and information from the Web, as uncovered in search-related patents and whitepapers.

These approaches may include natural language processing and knowledge bases, as well as how a search engine may do things such as question-answering.

Patents and papers involving concepts, entities, and knowledge Graphs will be covered by posts in this category.

Search Engine Queries May be Used to Identify Entity Attributes

by

How Search Engine Queries to Identify Entity Attributes What are query stream ontologies, and how might they change search? Search engines trained us to use keywords when we searched – to guess what words or phrases might be the best ones to try to find something we are interested in. That we might have a … Read more

Entities in the Google Knowledge Graph Search API for Google

by

Exploring The Google Knowledge Graph Search API The Google Knowledge Graph Search API on a query for Google shows the following Entities and results in scores for them. I thought they were diverse enough to be interesting and worth sharing. A couple of the ones listed seem odd, such as the Indian Action movie. “Thuppakki” … Read more

Google Patents Context Vectors to Improve Search

by
Context Vectors

Google Uses Context Vectors to Index the Meanings of Query Terms A limitation of information on the Web is how it gets organized differently at each site on the Web. A new Google patent on Context Vectors tells us there is no official catalog of information on the internet. Each site has its own organizational … Read more