@InProceedings{saito-EtAl:2017:I17-1,
  author    = {Saito, Itsumi  and  Nishida, Kyosuke  and  Sadamitsu, Kugatsu  and  Saito, Kuniko  and  Tomita, Junji},
  title     = {Automatically Extracting Variant-Normalization Pairs for Japanese Text Normalization},
  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     = {937--946},
  abstract  = {Social media texts, such as tweets from Twitter, contain many types of
	non-standard tokens, and the number of normalization approaches for handling
	such noisy text has been increasing. We present a method for automatically
	extracting pairs of a variant word and its normal form from unsegmented text on
	the basis of a pair-wise similarity approach. We incorporated the acquired
	variant-normalization pairs into Japanese morphological analysis. The
	experimental results show that our method can extract widely covered variants
	from large Twitter data and improve the recall of normalization without
	degrading the overall accuracy of Japanese morphological analysis.
	Author{1}{Affiliation}},
  url       = {http://www.aclweb.org/anthology/I17-1094}
}