How to find all Wikipedia pages related to a named entity?

Question

Given a text, I am looking to find links to all Wikipedia pages related to named entities mentioned in the text. Is there a reliable way to do this?

For example, consider the text,

Mark Elliot Zuckerberg is an American internet entrepreneur and philanthropist.

" Given this, I am looking at output with the following links:

• https://en.wikipedia.org/wiki/Mark_Zuckerberg
• https://en.wikipedia.org/wiki/Americans
• https://en.wikipedia.org/wiki/Internet
• https://en.wikipedia.org/wiki/Entrepreneurship
• https://en.wikipedia.org/wiki/Philanthropy

Is this possible at all given the current state of NLP? Many thanks!

Answer 1

The problem you are trying to solve is called Entity Linking. There are many academic papers discussing solutions to this problem, but only few of them provide an implementation.

OpenTapioka from Oxford has an open source implementation and an online demo.

SWAT from the University of Pisa has a publically available API.