@InProceedings{saito-EtAl:2017:I17-2,
  author    = {Saito, Itsumi  and  Suzuki, Jun  and  Nishida, Kyosuke  and  Sadamitsu, Kugatsu  and  Kobashikawa, Satoshi  and  Masumura, Ryo  and  Matsumoto, Yuji  and  Tomita, Junji},
  title     = {Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels},
  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     = {257--262},
  abstract  = {In this study, we investigated the effectiveness of augmented data for
	encoder-decoder-based neural normalization models. Attention based
	encoder-decoder models are greatly effective in generating many natural
	languages. % such as machine translation or machine summarization.
	In general, we have to prepare for a large amount of training data to train an
	encoder-decoder model. Unlike machine translation, there are few training data
	for text-normalization tasks. In this paper, we propose two methods for
	generating augmented data. The experimental results with Japanese dialect
	normalization indicate that our methods are effective for an encoder-decoder
	model and achieve higher BLEU score than that of baselines. We also
	investigated the oracle performance and revealed that there is 
	sufficient room for improving an encoder-decoder model.
	Author{1}{Affiliation}},
  url       = {http://www.aclweb.org/anthology/I17-2044}
}