@InProceedings{zhao-EtAl:2017:EMNLP20171,
  author    = {Zhao, Zhe  and  Liu, Tao  and  Li, Shen  and  Li, Bofang  and  Du, Xiaoyong},
  title     = {Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {244--253},
  abstract  = {The existing word representation methods mostly limit their information source
	to word co-occurrence statistics. In this paper, we introduce ngrams into four
	representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization.
	Comprehensive experiments are conducted on word analogy and similarity tasks.
	The results show that improved word representations are learned from ngram
	co-occurrence statistics. We also demonstrate that the trained ngram
	representations are useful in many aspects such as finding antonyms and
	collocations. Besides, a novel approach of building co-occurrence matrix is
	proposed to alleviate the hardware burdens brought by ngrams.},
  url       = {https://www.aclweb.org/anthology/D17-1023}
}