@inproceedings{nandakumar-etal-2019-well,
    title = "How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions",
    author = "Nandakumar, Navnita  and
      Baldwin, Timothy  and
      Salehi, Bahar",
    editor = "Rogers, Anna  and
      Drozd, Aleksandr  and
      Rumshisky, Anna  and
      Goldberg, Yoav",
    booktitle = "Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}",
    month = jun,
    year = "2019",
    address = "Minneapolis, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W19-2004/",
    doi = "10.18653/v1/W19-2004",
    pages = "27--34",
    abstract = "In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings suggest that Word2vec performs the best, followed by FastText and Infersent. Moreover, we find that recently-proposed contextualised embedding models such as Bert and ELMo are not adept at handling non-compositionality in multiword expressions."
}