@inproceedings{zobnin-elistratova-2019-learning,
    title = "Learning Word Embeddings without Context Vectors",
    author = "Zobnin, Alexey  and
      Elistratova, Evgenia",
    editor = "Augenstein, Isabelle  and
      Gella, Spandana  and
      Ruder, Sebastian  and
      Kann, Katharina  and
      Can, Burcu  and
      Welbl, Johannes  and
      Conneau, Alexis  and
      Ren, Xiang  and
      Rei, Marek",
    booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/W19-4329/",
    doi = "10.18653/v1/W19-4329",
    pages = "244--249",
    abstract = "Most word embedding algorithms such as word2vec or fastText construct two sort of vectors: for words and for contexts. Naive use of vectors of only one sort leads to poor results. We suggest using indefinite inner product in skip-gram negative sampling algorithm. This allows us to use only one sort of vectors without loss of quality. Our {\textquotedblleft}context-free{\textquotedblright} cf algorithm performs on par with SGNS on word similarity datasets"
}