@inproceedings{zhao-etal-2017-ngram2vec,
    title = "{N}gram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics",
    author = "Zhao, Zhe  and
      Liu, Tao  and
      Li, Shen  and
      Li, Bofang  and
      Du, Xiaoyong",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D17-1023/",
    doi = "10.18653/v1/D17-1023",
    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."
}