Zerogen: Efficient zero-shot learning via dataset generation
SEML: Self-Supervised Information-Enhanced Meta-learning for Few-Shot Text Classification
H Li, G Huang, Y Li, X Zhang, Y Wang, J Li - International Journal of …, 2023 - Springer
Training a deep-learning text classification model usually requires a large amount of labeled
data, yet labeling data are usually labor-intensive and time-consuming. Few-shot text …
data, yet labeling data are usually labor-intensive and time-consuming. Few-shot text …
Improving question answering performance using knowledge distillation and active learning
Contemporary question answering (QA) systems, including Transformer-based
architectures, suffer from increasing computational and model complexity which render them …
architectures, suffer from increasing computational and model complexity which render them …