AI Paper Spotlights - Regression-Free Model Updates for Spoken Language Understanding
Join us for the next AI Paper Spotlights - Berlin’s AI Research Meet Up as we dive into the latest advancements in the dynamic world of AI 🚀
In real-world systems, an important requirement for model updates is to avoid regressions in user experience caused by flips of previously correct classifications to incorrect ones. In this talk, Verena Weber, previously Research Scientist II at Amazon Alexa AI, will introduce a technique, focal distillation, to reduce such regressions during model updates and evaluate its usefulness in a real-world dialog system.