ep46: FreeLB: Enhanced Adversarial Training for Language Understanding
Jan 01, 2020•24 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
ICLR 2020より，BERT/RoBERTaの埋め込み空間に，敵対摂動を入れるVirtual Adversarial Trainingによって，モデル性能を改善するFreeLBという手法を解説しました．
今回紹介した記事はこちらのissueで解説しています． https://github.com/jojonki/arXivNotes/issues/347
サポーターも募集中です． https://www.patreon.com/jojonki
For the best experience, listen in Metacast app for iOS or Android