Papers with prediction trials

1 papers
Mitigating Uncertainty in Document Classification (N19-1)

Copied to clipboard

Challenge: Existing models for uncertainty measurement are time-consuming and unable to handle large-scale data sets.
Approach: They propose a new dropout-entropy method for uncertainty measurement and a metric learning method on feature representations to boost the performance of dropout based uncertainty methods.
Outcome: The proposed method improves accuracy from 0.78 to 0.92 when 30% of the most uncertain predictions were handed over to human experts in “20NewsGroup” data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations