Skip to content
SOTA machine translation at Unbabel (Practical AI #204) episode artwork

Dec 13, 2022 30 min

SOTA machine translation at Unbabel (Practical AI #204)

from Changelog Master Feed

José and Ricardo joined Daniel at EMNLP 2022 to discuss state-of-the-art machine translation, the WMT shared tasks, and quality estimation. Among other things, they talk about Unbabel's innovations in quality estimation including COMET, a neural framework for training multilingual machine translation (MT) evaluation models.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

SOTA machine translation at Unbabel (Practical AI #204)

0:00 30:28

Chapters

  1. 0:00 Opener
  2. 0:57 Welcome to Practical AI
  3. 1:40 Unbabel
  4. 6:24 So much more than a confidence score
  5. 10:41 Quality estimation
  6. 14:37 When words don't align
  7. 21:52 KNNMT
  8. 24:32 This gets us excited
  9. 28:02 Find out more
  10. 29:41 Outro

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Changelog Master Feed?

This episode is 30 minutes long.

When was this Changelog Master Feed episode published?

This episode was published on December 13, 2022.

Is there a transcript available for this episode?

Yes, a full transcript is available for this episode. You can read the complete transcript on the episode page.

Can I download this Changelog Master Feed episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.