Demystifying SQuAD-style Question Answering Systems

Let’s walk through the main stages of state-of-the-art question answering systems. Reference to code will accompany this explanation so that you can get started building your own industry ready system.

Question answering (QA) has come along in leaps and bounds over the last couple years. Just one year ago, the SQuAD 2.0 benchmark was smashed overnight by BERT when it outperformed NLNet by 6% F1. Since then…

To keep reading this story, create a free account.

Already have an account? Sign in

Branden Chan

Written by

Machine Learning Engineer at deepset.ai developing cutting edge NLP systems

Towards Data Science

A Medium publication sharing concepts, ideas, and codes.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade