Upcoming Talks

Ista white

Neural Machine Translation Inside Out

Date
Wednesday, November 10, 2021 16:00 - 18:00
Speaker
Lena Voita (University of Edinburgh)
Location
Zoom Link: https://istaustria.zoom.us/j/94284847467?pwd=VXlZZjhtTEpZbUpGRHBId3liM1k0UT09 Meeting ID: 942 8484 7467 Passcode: 719116
Series
Seminar/Talk
Tags
ELLIS talk
Host
Marco Mondelli
Contact
Ksenja Harpprecht

In the last decade, machine translation shifted from traditional statistical approaches (SMT) to end-to-end neural ones (NMT). While traditional approaches split the translation task into several components and use various hand-crafted features, NMT learns the translation task directly from data, without splitting it into subtasks. The main question of this talk is how NMT manages to do this, and I will try to answer it keeping in mind the traditional paradigm. First, I will show that NMT components can take roles corresponding to the features modelled explicitly in SMT. Then I will explain how NMT balances the two different types of context, the source and the prefix of the target sentence. Finally, we will see that NMT training consists of the stages where it focuses on the competences mirroring three core SMT components: target-side language modeling, lexical translation, and reordering.


Qr image
Download ICS Download invitation
Back to eventlist