@inproceedings{stap-monz-2023-multilingual,
    title = "Multilingual $k$-Nearest-Neighbor Machine Translation",
    author = "Stap, David  and
      Monz, Christof",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.emnlp-main.571/",
    doi = "10.18653/v1/2023.emnlp-main.571",
    pages = "9200--9208",
    abstract = "\textit{k}-nearest-neighbor machine translation has demonstrated remarkable improvements in machine translation quality by creating a datastore of cached examples. However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. Our results consistently demonstrate substantial improvements not only in low-resource translation quality (up to $+3.6$ BLEU), but also for high-resource translation quality (up to $+0.5$ BLEU). Our experiments show that it is possible to create multilingual datastores that are a quarter of the size, achieving a 5.3x speed improvement, by using linguistic similarities for datastore creation."
}