@inproceedings{tokarchuk-niculae-2024-unreasonable,
    title = "The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation",
    author = "Tokarchuk, Evgeniia  and
      Niculae, Vlad",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.naacl-short.56/",
    doi = "10.18653/v1/2024.naacl-short.56",
    pages = "653--662",
    abstract = "Continuous-output neural machine translation (CoNMT) replaces the discrete next-word prediction problem with an embedding prediction.The semantic structure of the target embedding space (*i.e.*, closeness of related words) is intuitively believed to be crucial. We challenge this assumption and show that completely random output embeddings can outperform laboriously pre-trained ones, especially on larger datasets. Further investigation shows this surprising effect is strongest for rare words, due to the geometry of their embeddings. We shed further light on this finding by designing a mixed strategy that combines random and pre-trained embeddings, and that performs best overall."
}