@InProceedings{zhang-wallace:2017:I17-1,
  author    = {Zhang, Ye  and  Wallace, Byron},
  title     = {A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {253--263},
  abstract  = {Convolutional Neural Networks (CNNs) have recently achieved remarkably strong
	performance on the practically important task of sentence classification (Kim,
	2014; Kalchbrenner et al., 2014; Johnson and Zhang, 2014; Zhang et al., 2016).
	However, these models require practitioners to specify an exact model
	architecture and set accompanying hyperparameters, including the filter region
	size, regularization parameters, and so on. It is currently unknown
	how sensitive model performance is to changes in these configurations for the
	task of sentence classification. We thus conduct a sensitivity analysis of
	one-layer CNNs to explore the effect of architecture components on model
	performance; our aim is to distinguish between important
	and comparatively inconsequential design decisions for sentence classification.
	We focus on one-layer CNNs (to the exclusion of more complex models) due to
	their comparative simplicity and strong empirical performance, which makes it a
	modern standard baseline method akin to Support Vector Machine (SVMs) and
	logistic regression. We derive practical advice from our extensive empirical
	results for those interested in getting the most out of CNNs for sentence
	classification in real world settings.},
  url       = {http://www.aclweb.org/anthology/I17-1026}
}