Skip to content

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation.

Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md. Akmal Haidar, Ali Ghodsi

VenueA*EMNLP
Year2021
ProceedingsEMNLP (1)

Browse the full EMNLP paper archive.