When in Doubt: Improving Classification Performance with Alternating Normalization

Menglin Jia; Austin Reiter; Ser-Nam Lim; Yoav Artzi; Claire Cardie

EMNLP 2021finding16 citations

When in Doubt: Improving Classification Performance with Alternating Normalization

Menglin Jia, Austin Reiter, Ser-Nam Lim, Yoav Artzi, Claire Cardie

Abstract

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.

BibTeX

@inproceedings{jia-etal-2021-doubt-improving,
    title = "When in Doubt: Improving Classification Performance with Alternating Normalization",
    author = "Jia, Menglin  and
      Reiter, Austin  and
      Lim, Ser-Nam  and
      Artzi, Yoav  and
      Cardie, Claire",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.148/",
    doi = "10.18653/v1/2021.findings-emnlp.148",
    pages = "1716--1723"
}