Deep Learning for Machine Translation: a paradigm shift

15:10/15:50

In beginning there was the "rule based" machine translation, like Babelfish, that didn't work at all. Then came the Statistical Machine translation, powering the like of Google Translate, and all was good. Nowadays, it's all about Deep Learning and the Neural Machine Translation is the state of the art, with unmatched translation fluency. Let's dive into the internals of a Neural Machine Translation system, explaining the principles and the advantages over the past.

Language: Italian

Level: Advanced

Alberto Massidda

ML/DL Advocate - Sourcesense

Computer engineer with 10 years of experience, specialized in mission critical, high traffic flow, high available architectures and infrastructures, on Linux platforms, with a relevant experience in development and management of web and cloud services. He has served as Infrastructure Lead in 3 companies. Alberto has a variegated bundle of experience, that ranges from devops to machine learning, from the corporate banking to the mutable startup world.

Go to speaker's detail