🗺 Edge#214: NLLB-200, Meta AI’s New Super Model that Achieved New Milestones in Machine Translations Across 200 Languages
One of the most important achievements to bring machine translation to low-resource languages
On Thursdays, we dive deep into one of the freshest research papers or technology frameworks that is worth your attention. Our goal is to keep you up to date with new developments in AI to complement the concepts we debate in other editions of our newsletter.
💥 What’s New in AI: NLLB-200, Meta AI’s New Super Model that Achieved New Milestones in Machine Translations Across 200 Languages
Machine translation is one of the deep learning disciplines that can have an immediate social impact. These days, there are large segments of the world population that can’t access online content in their native languages. Similarly, most of the advancements in natural language understanding (NLU) have been constrained to high-resource languages such as English, Spanish or French that have vast volumes of training data available. Expanding translations to hundreds of low-resource languages and dialects is one of the most critical challenges of the next decade of machine translation. Recently, Meta AI open-sourced no language left behind (NLLB)-200, a model that can perform state-of-the-art machine translation across 200 languages. Meta AI also open-sourced a few complementary datasets and frameworks that can help expedite research in machine translation for low-resource languages. The research paper for NLLB-200 is an astonishing 190 pages long. Let’s dive into it!