Asking a question to a machine and receiving an answer was always the stuff of sci-fi in the not too distant past. Now, things have changed, and we find ourselves using Q&A systems everywhere — without even realizing it.
Google search is the best example — although in most cases Google is used to find information and will simply point you in the right direction, many other queries are direct questions — to which Google often provides direct answers.
Of course, Google is ahead of the game. But that doesn’t mean that we can’t produce great Q&A systems — we can — and we can even use the exact same models that Google uses in their search.
In this video, we will learn how to use state-of-the-art transformer models for Q&A. We will take a look at Google’s Bert and how to use it.
#python #huggingface #tensorflow #pytorch #machine-learning #deep-learning