Yuehuan He
Yuehuan He
Home
Publications
Experience
Posts
Other
Light
Dark
Automatic
Self Training
SIAST: A Slot Imbalance-Aware Self-Training Scheme for Semi-Supervised Slot Filling
This paper proposes a novel self-training scheme SIAST for imbalanced slot filling that aims to learn unbiased margins between slot classes while mitigating potential slot confusion, and adaptively samples pseudo-labelled data to balance the slot distribution of the training set.
Jiachi Liu
,
Sishi Xiong
,
Yuehuan He
,
Tong Zhou
,
Liwen Wang
,
Xuefeng Li
,
Bo Xiao
PDF
Code
DOI
Cite
×