{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Practical AI","title":"SOTA machine translation at Unbabel","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/3d390eaa\"></iframe>","width":"100%","height":180,"duration":1826,"description":"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.Featuring:Ricardo Rei – XJosé Souza – XDaniel Whitenack – Website, GitHub, XShow Notes:UnbabelCOMETThe WMT workshop/ conferenceEMNLPUpcoming Events: Register for upcoming webinars here!","thumbnail_url":"https://img.transistorcdn.com/Ox7ZlyiQOhdDa4Qy1MnJH5WFoksAetrzb40Jo1pePFs/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wMTZi/ZWJmNWIwNDdmYTcw/NGJjMTExZjNjZmYy/M2ZjNS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}