@inproceedings{gordon-etal-2021-data,
    title = "Data and Parameter Scaling Laws for Neural Machine Translation",
    author = "Gordon, Mitchell A  and
      Duh, Kevin  and
      Kaplan, Jared",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2021.emnlp-main.478/",
    doi = "10.18653/v1/2021.emnlp-main.478",
    pages = "5915--5922",
    abstract = "We observe that the development cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and the number of non-embedding parameters in the model. We discuss some practical implications of these results, such as predicting BLEU achieved by large scale models and predicting the ROI of labeling data in low-resource language pairs."
}