Practical AI: Machine Learning, Data Science, LLM

SOTA machine translation at Unbabel

Dec 13, 2022

30:28

Creator website

AI Chapters

Episode notes

Introduction

2min

Unbabel at EMNLP 2022

5min

The Different Types of Machine Translation Metrics

4min

The Different Types of Quality Estimation

4min

The Challenges to Quality Estimation and Metrics

4min

The Importance of Using Bigger Models

3min

KNN MT for Chat Share Tasks

3min

The Future of Machine Translation

4min

Unbabel and the Future of AI

2min

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.

Join the discussion

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

Featuring: