English

Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing

Computation and Language 2020-10-08 v1 Machine Learning Methodology

Abstract

Recent work raises concerns about the use of standard splits to compare natural language processing models. We propose a Bayesian statistical model comparison technique which uses k-fold cross-validation across multiple data sets to estimate the likelihood that one model will outperform the other, or that the two will produce practically equivalent results. We use this technique to rank six English part-of-speech taggers across two data sets and three evaluation metrics.

Keywords

Cite

@article{arxiv.2010.03088,
  title  = {Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing},
  author = {Piotr Szymański and Kyle Gorman},
  journal= {arXiv preprint arXiv:2010.03088},
  year   = {2020}
}

Comments

Accepted to EMNLP2020

R2 v1 2026-06-23T19:06:33.599Z