Lilt Labs | Bridging Translation Research and Practice

Lilt's Favorite Neural Machine Translation Videos

Written by Lilt Labs | August, 27, 2018

Neural Machine Translation is everywhere (and not just on this blog). Translators want to know how it will affect their livelihood, and internal localization managers want to know how they can make it work for their translation strategy. Whether you're looking to assess the business applications of neural machine translation, or peek under the hood to see how all the gears fit together, these NMT videos can help you wrap your head around the rising tide that is neural machine translation.

Neural Machine Translation and Models with Attention 

This video is a full lecture from Stanford's School of Engineering. The lecturer, Chris Manning--Thomas M. Siebel Professor in Machine Learning, Professor of Linguistics and Computer Science--emphasizes how to implement, train, debug, visualize, and design neural network models.

The Wonderful and Terrifying Implications of Computers That Can Learn 











While only tangentially related to NMT, this TED talk covers several examples of Deep Learning, or a computer's ability to process information and create output of their own accord. Included is an exciting real time audio translation from English to Chinese.

What do Neural Machine Translation Models Learn about Morphology?



It's well documented, but NMT presents an opportunity not just to include morphology features, but also for the technology to learn from the translator and provide more accurate feedback. What can NMT tools learn about morphology? A slew of MIT professors give you the bangers & mash. 

Business Applications of NMT

University of Zurich PhD candidate, CTO of TechShuttle, and Researcher at Lilt Samuel Läubli explains the growing corporate utility and needs of NMT at last year's SlatorCon translation conference. You'll have to click through to view the video on Vimeo, but it's worth it.

How Can NMT Make Translators Better?

Some translators fear that NMT threatens to make them obsolete, but at Lilt, we're convinced it's only going to make language professionals more efficient and better at their jobs. Here's a breakdown of how human translators can utilize NMT to continue creating nuanced, geo-specific translation work.

What are you favorite free NMT resources? Hit us up in the comments!