@inproceedings{zhang-zweigenbaum-2018-gneg,
    title = "{GNEG}: Graph-Based Negative Sampling for word2vec",
    author = "Zhang, Zheng  and
      Zweigenbaum, Pierre",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/P18-2090/",
    doi = "10.18653/v1/P18-2090",
    pages = "566--571",
    abstract = "Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5{\%} and improves the performance on word similarity tasks by about 1{\%} compared to the skip-gram negative sampling baseline."
}