Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification
Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification
Xiang Jiang,Mohammad Havaei,5 Authors,S. Matwin
2018
31 Citations
TLDR
The proposed Attentive Task-Agnostic Meta-Learning (ATAML) algorithm for text classification is designed to encourage task-agnostic representation learning by way of task-gnostic parameterization and facilitate task-speci fic adaptation via attention mechanisms.