spaCy is an open-source library for advanced Natual Language Processing in Python. In this video, we show you how to create a custom Entity Linking model in spaCy to disambiguate different mentions of the person “Emerson” to unique identifiers in a knowledge base. We accomplish this by training a machine learning model on some text annotated from scratch with Prodigy. You can follow along in this notebook: https://github.com/explosion/projects/tree/master/nel-emerson/scripts/notebook_video.ipynb

STEP BY STEP
00:00 – Introduction to the Entity Linking challenge
04:52 – Set up the knowledge base
10:30 – Annotate training data with Prodigy
19:19 – Parse the training data into the required format for spaCy
23:12 – Create and train the Entity Linking component
25:36 – Test the EL component on unseen data

SPACY & PRODIGY
● spaCy: https://spacy.io
● Free online course: https://course.spacy.io
● Prodigy website & docs: https://prodi.gy

THIS TUTORIAL
● Code & data: https://github.com/explosion/projects/tree/master/nel-emerson/
● Entity linking in spaCy (spaCy IRL talk): https://www.youtube.com/watch?v=PW3RJM8tDGo&list=PLBmcuObd5An4UC6jvK_-eSl6jCvP1gwXc&index=6
● Entity linking docs: https://spacy.io/usage/training#entity-linker

FOLLOW US
● Sofie Van Landeghem: https://twitter.com/OxyKodit
● Explosion: https://twitter.com/explosion_ai