Open in app
Alexander Veysov
77 Followers
About

Sign in

77 Followers
About
Open in app
Alexander Veysov

Alexander Veysov

Nov 13, 2018·1 min read

Well, this is really nice, but how is this different from BPE / char level models? In my practice bag-of-ngram based models worked best, even though I struggled to apply them for NMT.

Alexander Veysov

Data Scientist

Why you should care about byte-level sequence-to-sequence models in NLP
233
2

Tom Kenter

More from Alexander Veysov

Data Scientist

More From Medium

Towards an ImageNet Moment for Speech-to-Text

Alexander Veysov in Towards Data Science

Russian Open Speech To Text (STT/ASR) Dataset

Alexander Veysov in Towards Data Science

Playing with Nvidia’s New Ampere GPUs and Trying MIG

Alexander Veysov in Towards Data Science

Complexity / generalization /computational cost in NLP modeling of morphologically rich languages

Alexander Veysov in Towards Data Science

Chris Hemsworth Is Exactly What’s Wrong With The Fitness Industry

Daniel Hopper in Better Marketing

The Future is More Terrifying Than We Can Imagine

Alastair Isaacs in Predict

Why Is The Age of Consent in Japan Only 13-Year-Old?

Isaiah McCall in History of Yesterday

The Fate Of Elon Musk’s Assistant Is A Cautionary Tale For Negotiating Salary

Nick Wolny in Entrepreneur's Handbook

About

Help

Legal

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store