@inproceedings{marchisio-etal-2022-isovec,
    title = "{I}so{V}ec: Controlling the Relative Isomorphism of Word Embedding Spaces",
    author = "Marchisio, Kelly  and
      Verma, Neha  and
      Duh, Kevin  and
      Koehn, Philipp",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.emnlp-main.404/",
    doi = "10.18653/v1/2022.emnlp-main.404",
    pages = "6019--6033",
    abstract = "The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces{---}their degree of {\textquotedblleft}isomorphism.{\textquotedblright} We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the skipgram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec."
}