@InProceedings{liu-EtAl:2018:C18-13,
  author    = {Liu, Rui  and  Bao, Feilong  and  Gao, Guanglai  and  Zhang, Hui  and  Wang, Yonghe},
  title     = {A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {2448--2455},
  abstract  = {In this paper, we first utilize the word embedding that focuses on sub-word units to the Mongolian Phrase Break (PB) prediction task by using Long-Short-Term-Memory (LSTM) model. Mongolian is an agglutinative language. Each root can be followed by several suffixes to form probably millions of words, but the existing Mongolian corpus is not enough to build a robust entire word embedding, thus it suffers a serious data sparse problem and brings a great difficulty for Mongolian PB prediction. To solve this problem, we look at sub-word units in Mongolian word,},
  url       = {http://www.aclweb.org/anthology/C18-1207}
}