Spence Green — Enterprise-scale Machine Translation

Spence shares his experience creating a product around human-in-the-loop machine translation, and explains how machine translation has evolved over the years.---Spence Green is co-founder and CEO of Lilt, an AI-powered language translation platform. Lilt combines human translators and machine translation in order to produce high-quality translations more efficiently. ---🌟 Show notes:- http://wandb.me/gd-spence-green- Transcription of the episode- Links to papers, projects, and people⏳ Timestamps:0:00 Sneak peak, intro0:45 The story behind Lilt3:08 Statistical MT vs neural MT6:30 Domain adaptation and personalized models8:00 The emergence of neural MT and development of Lilt13:09 What success looks like for Lilt18:20 Models that self-correct for gender bias19:39 How Lilt runs its models in production26:33 How far can MT go?29:55 Why Lilt cares about human-computer interaction35:04 Bilingual grammatical error correction37:18 Human parity in MT39:41 The unexpected challenges of prototype to production---Get our podcast on these platforms:👉 Apple Podcasts: http://wandb.me/apple-podcasts​​👉 Spotify: http://wandb.me/spotify​👉 Google Podcasts: http://wandb.me/google-podcasts​​👉 YouTube: http://wandb.me/youtube​​👉 Soundcloud: http://wandb.me/soundcloud​Join our community of ML practitioners where we host AMAs, share interesting projects and meet other people working in Deep Learning:http://wandb.me/slack​​Check out Fully Connected, which features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, industry leaders sharing best practices, and more:https://wandb.ai/fully-connected