Problem Statement

Build an entity linker in two stages: find mentions in the text, then resolve each mention to an entry in a knowledge base. The Michael Jordan example shows why recognizing a person’s name does not yet identify which person the text means.

Introduction

Named entity linking (NEL) is the process of detecting and linking entity mentions in a given text to corresponding entities in a target knowledge base.

There are two parts to entity linking:

1. Named-entity recognition

   Named-entity recognition (NER) detects and classifies potential named entities in the text into predefined categories such as a person, organization, location, medical code, time expression, etc. (multi-class prediction).

2. Disambiguation

   Next, disambiguation disambiguates each detected entity by linking it to its corresponding entity in the knowledge base.

Note: The target knowledge base depends on the application, but for generic systems, a common choice is Wikidata or DBpedia.

Let’s see entity linking in action in the following example.