TanL. x 3

bookRéférences 3

Unirex: A unified learning framework for language model rationale extraction

… the sentiment analysis task. For task performance, Ftask is trained via gold label y* i...

2022-06-28 00:00:00

SanjabiM.TanL.ChanA.MathiasL.

MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding

To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which tr...

2021-01-01 00:00:00

JinW.SanjabiM.NieS.TanL.RenX.

Modality-specific distillation

… The task is a binary classification problem, which is to detect hate speech in multimod...

2021-01-01 00:00:00

JinW.SanjabiM.NieS.TanL.RenX.

Mots-clés associés