When in Doubt: Improving Classification Performance with Alternating Normalization

Autor:	Jia, Menglin, Reiter, Austin, Lim, Ser-Nam, Artzi, Yoav, Cardie, Claire
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability distribution using the predicted class distributions of high-confidence validation examples. CAN is easily applicable to any probabilistic classifier, with minimal computation overhead. We analyze the properties of CAN using simulated experiments, and empirically demonstrate its effectiveness across a diverse set of classification tasks. Comment: Findings of EMNLP 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.13449 Zobrazit plný text záznamu View this record from Arxiv