Extract and Disambiguate named entities.
Our Concept Extraction endpoint is a more accurate, more targeted and Linked Data-aware variation of our Entity Extraction endpoint.
Not only can you find out what topics are mentioned in a piece of text, but also you will be provided with their semantic types and URIs, which would allow you to dive deeper into Linked Data to bring in additional, relevant content.
Under the hood, our Concept Extraction endpoint performs very accurate Word Sense Disambiguation to find out what the author meant by each mentioned topic. For instance, does “apple” refer to the fruit or the company?
Concept Extraction Example:
We want to extract concepts from the following article:”http://www.bbc.com/sport/0/football/25912393″