Semanlink - Favoris ; Artificial Intelligence ; Task augmentation AND Few-shot learning

Impression

Recherche de Mot-clé

Recherche de Doc

Préférences...

Mots-clés liés

Arxiv Doc - EMNLP 2021 - Few-shot learning - NLP: intermediate-task training - NLP@Google - Quoc V. Le - Self-training - Task augmentation - Text Classification - Tweet -

Favoris ; Artificial Intelligence ; Task augmentation AND Few-shot learning

Descendants partagés

2 Documents

[2109.06270] STraTA: Self-Training with Task Augmentation for Better Few-shot Learning

Tags:

2022-04-14 A propos

Tu Vu sur Twitter : "Enormous LMs like GPT-3 exhibit impressive few-shot performance, but w/ self-training a BERT base sized model can achieve much better results!

Tags:

2022-04-13 A propos