@inproceedings{pickard-2020-comparing,
    title = "Comparing word2vec and {G}lo{V}e for Automatic Measurement of {MWE} Compositionality",
    author = "Pickard, Thomas",
    editor = "Markantonatou, Stella  and
      McCrae, John  and
      Mitrovi{\'c}, Jelena  and
      Tiberius, Carole  and
      Ramisch, Carlos  and
      Vaidya, Ashwini  and
      Osenova, Petya  and
      Savary, Agata",
    booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons",
    month = dec,
    year = "2020",
    address = "online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.mwe-1.12/",
    pages = "95--100",
    abstract = "This paper explores the use of word2vec and GloVe embeddings for unsupervised measurement of the semantic compositionality of MWE candidates. Through comparison with several human-annotated reference sets, we find word2vec to be substantively superior to GloVe for this task. We also find Simple English Wikipedia to be a poor-quality resource for compositionality assessment, but demonstrate that a sample of 10{\%} of sentences in the English Wikipedia can provide a conveniently tractable corpus with only moderate reduction in the quality of outputs."
}