@inproceedings{shwartz-2019-systematic,
    title = "A Systematic Comparison of {E}nglish Noun Compound Representations",
    author = "Shwartz, Vered",
    editor = "Savary, Agata  and
      Escart{\'i}n, Carla Parra  and
      Bond, Francis  and
      Mitrovi{\'c}, Jelena  and
      Mititelu, Verginica Barbu",
    booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W19-5111/",
    doi = "10.18653/v1/W19-5111",
    pages = "92--103",
    abstract = "Building meaningful representations of noun compounds is not trivial since many of them scarcely appear in the corpus. To that end, composition functions approximate the distributional representation of a noun compound by combining its constituent distributional vectors. In the more general case, phrase embeddings have been trained by minimizing the distance between the vectors representing paraphrases. We compare various types of noun compound representations, including distributional, compositional, and paraphrase-based representations, through a series of tasks and analyses, and with an extensive number of underlying word embeddings. We find that indeed, in most cases, composition functions produce higher quality representations than distributional ones, and they improve with computational power. No single function performs best in all scenarios, suggesting that a joint training objective may produce improved representations."
}