@InProceedings{asano-mizumoto-inui:2017:I17-2,
  author    = {Asano, Hiroki  and  Mizumoto, Tomoya  and  Inui, Kentaro},
  title     = {Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {343--348},
  abstract  = {In grammatical error correction (GEC), automatically evaluating system outputs
	requires gold-standard references, which must be created manually and thus tend
	to be both expensive and limited in coverage. To address this problem, a
	reference-less approach has recently emerged; however, previous reference-less
	metrics that only consider the criterion of grammaticality, have not worked as
	well as reference-based metrics. This study explores the potential of extending
	a prior grammaticality-based method to establish a reference-less evaluation
	method for GEC systems. Further, we empirically show that a reference-less
	metric that combines fluency and meaning preservation with grammaticality
	provides a better estimate of manual scores than that of commonly used
	reference-based metrics. To our knowledge, this is the first study that
	provides empirical evidence that a reference-less metric can replace
	reference-based metrics in evaluating GEC systems.},
  url       = {http://www.aclweb.org/anthology/I17-2058}
}