SOTA machine translation at Unbabel
Publisher |
Changelog Media
Media Type |
audio
Categories Via RSS |
Software How-To
Tech News
Technology
Publication Date |
Dec 13, 2022
Episode Duration |
00:30:28
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.
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.

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.

Leave us a comment

Changelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!

Featuring:

Show Notes:

Something missing or broken? ai-204.md">PRs welcome!

Timestamps:

(00:00) - Opener(00:57) - Welcome to Practical AI(01:40) - Unbabel(06:24) - So much more than a confidence score(10:41) - Quality estimation(14:37) - When words don't align(21:52) - KNNMT(24:32) - This gets us excited(28:02) - Find out more(29:41) - Outro

This episode currently has no reviews.

Submit Review
This episode could use a review!

This episode could use a review! Have anything to say about it? Share your thoughts using the button below.

Submit Review