all AI news
Improving Imbalanced Text Classification with Dynamic Curriculum Learning. (arXiv:2210.14724v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
Recent advances in pre-trained language models have improved the performance
for text classification tasks. However, little attention is paid to the
priority scheduling strategy on the samples during training. Humans acquire
knowledge gradually from easy to complex concepts, and the difficulty of the
same material can also vary significantly in different learning stages.
Inspired by this insights, we proposed a novel self-paced dynamic curriculum
learning (SPDCL) method for imbalanced text classification, which evaluates the
sample difficulty by both linguistic character …
arxiv classification curriculum curriculum learning text text classification