@inproceedings{ali-etal-2023-gari,
    title = "{GARI}: Graph Attention for Relative Isomorphism of {A}rabic Word Embeddings",
    author = "Ali, Muhammad  and
      Alshmrani, Maha  and
      Qin, Jianbin  and
      Hu, Yan  and
      Wang, Di",
    editor = "Sawaf, Hassan  and
      El-Beltagy, Samhaa  and
      Zaghouani, Wajdi  and
      Magdy, Walid  and
      Abdelali, Ahmed  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Habash, Nizar  and
      Khalifa, Salam  and
      Keleg, Amr  and
      Haddad, Hatem  and
      Zitouni, Imed  and
      Mrini, Khalil  and
      Almatham, Rawan",
    booktitle = "Proceedings of ArabicNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.arabicnlp-1.16/",
    doi = "10.18653/v1/2023.arabicnlp-1.16",
    pages = "181--190",
    abstract = "Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95{\%} and 76.80{\%} for in-domain and domain mismatch settings respectively."
}