Linear Digressions

Zero Shot Translation

Linear Digressions

Take Google-size data, the flexibility of a neural net, and all (well, most) of the languages of the world, and what you end up with is a pile of surprises. This episode is about some interesting features of Google's new neural machine translation system, namely that with minimal tweaking, it can accommodate many different languages in a single neural net, that it can do a half-decent job of translating between language pairs it's never been explicitly trained on, and that it seems to have its own internal representation of concepts that's independent of the language those concepts are being represented in. Intrigued? You should be...

Next Episodes

Linear Digressions

Google Neural Machine Translation @ Linear Digressions

📆 2017-01-02 02:44 / 00:18:12




Linear Digressions

How to Lose at Kaggle @ Linear Digressions

📆 2016-12-12 05:28 / 00:17:16


Linear Digressions

Attacking Discrimination in Machine Learning @ Linear Digressions

📆 2016-12-05 04:38 / 00:23:20