@InProceedings{fujinuma-grissomii:2017:I17-2,
  author    = {Fujinuma, Yoshinari  and  Grissom II, Alvin},
  title     = {Substring Frequency Features for Segmentation of Japanese Katakana Words with Unlabeled Corpora},
  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     = {74--79},
  abstract  = {Word segmentation is crucial in natural language processing tasks for
	unsegmented languages. In Japanese, many out-of-vocabulary words appear in the
	phonetic syllabary katakana, making segmentation more difficult due to the lack
	of clues found in mixed script settings. In this paper, we propose a
	straightforward approach based on a variant of tf-idf and apply it to the
	problem of word segmentation in Japanese. Even though our method uses only an
	unlabeled corpus, experimental results show that it achieves performance
	comparable to existing methods that use manually labeled corpora. Furthermore,
	it improves performance of simple word segmentation models trained on a
	manually labeled corpus.},
  url       = {http://www.aclweb.org/anthology/I17-2013}
}