@inproceedings{guta-etal-2025-green,
    title = "The Green {KNIGHT}: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformers",
    author = "Guta, Andreas  and
      Petrick, Frithjof  and
      Pol{\'a}k, Peter",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.316/",
    doi = "10.18653/v1/2025.findings-emnlp.316",
    pages = "5916--5931",
    ISBN = "979-8-89176-335-7",
    abstract = "State-of-the-art neural machine translation (NMT) models deliver high-quality translations at the expense of high inference latency and energy consumption, requiring vast GPU fleets and contributing significantly to carbon emissions. To democratize and ``green'' NMT, we introduce the Green KNIGHT, a hardware-agnostic collection of recipes to optimize translation speed and energy consumption, with only a moderate trade-off in quality. On high-resource En{\textrightarrow}De and En{\textrightarrow}Ko benchmarks, we achieve up to 117{\texttimes} CPU speedup and 98.2{\%} energy savings with 9{\%} relative BLEU decrease. On WMT 2014 En{\textrightarrow}De and En{\textrightarrow}Fr benchmarks, we obtain up to 140{\texttimes} speedup with 98.7{\%} energy savings, while staying within 10{--}12{\%} relative BLEU decrease. Our results demonstrate that efficient and environmentally conscious NMT can be realized through optimizations built on well-understood, off-the-shelf techniques with no custom low-level code required, making our approach immediately deployable in real-world translation pipelines."
}