@inproceedings{schlechtweg-etal-2019-second,
    title = "Second-order Co-occurrence Sensitivity of Skip-Gram with Negative Sampling",
    author = "Schlechtweg, Dominik  and
      Oguz, Cennet  and
      Schulte im Walde, Sabine",
    editor = "Linzen, Tal  and
      Chrupa{\l}a, Grzegorz  and
      Belinkov, Yonatan  and
      Hupkes, Dieuwke",
    booktitle = "Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-4803/",
    doi = "10.18653/v1/W19-4803",
    pages = "24--30",
    abstract = "We simulate first- and second-order context overlap and show that Skip-Gram with Negative Sampling is similar to Singular Value Decomposition in capturing second-order co-occurrence information, while Pointwise Mutual Information is agnostic to it. We support the results with an empirical study finding that the models react differently when provided with additional second-order information. Our findings reveal a basic property of Skip-Gram with Negative Sampling and point towards an explanation of its success on a variety of tasks."
}