@InProceedings{yang-zhang-dong:2017:Long,
  author    = {Yang, Jie  and  Zhang, Yue  and  Dong, Fei},
  title     = {Neural Word Segmentation with Rich Pretraining},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {839--849},
  abstract  = {Neural word segmentation research has benefited from large-scale raw texts by
	leveraging them for pretraining character and word embeddings. On the other
	hand, statistical segmentation research has exploited richer sources of
	external information, such as punctuation, automatic segmentation and POS. We
	investigate the effectiveness of a range of external training sources for
	neural word segmentation by building a modular segmentation model, pretraining
	the most important submodule using rich external sources. Results show that
	such pretraining significantly improves the model, leading to accuracies
	competitive to the best methods on six benchmarks.},
  url       = {http://aclweb.org/anthology/P17-1078}
}

