Lune

EMNLP Findings2025

The Green KNIGHT: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformers

Andreas Guta, Frithjof Petrick, Peter Polák

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 hardwareagnostic collection of recipes to optimize translation speed and energy consumption, with only a moderate trade-off in quality. On highresource En→De and En→Ko benchmarks, we achieve up to 117× CPU speedup and 98.2% energy savings with 9% relative BLEU decrease. On WMT 2014 En→De and En→Fr benchmarks, we obtain up to 140× 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-theshelf techniques with no custom low-level code required, making our approach immediately deployable in real-world translation pipelines.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. COMET: A Neural Framework for MT EvaluationRicardo Rei, Craig Stewart, Ana C. Farinha, Alon LavieEMNLP 2020 · 6 citations
  2. Bag of Tricks for Optimizing Transformer EfficiencyYe Lin, Yanyang Li, Tong Xiao, Jingbo ZhuEMNLP Findings 2021 · 4 citations
  3. Language-agnostic BERT Sentence EmbeddingFangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan et al.ACL 2022

Related papers

  1. Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationJungo Kasai, Nikolaos Pappas, Hao Peng, James Cross et al.ICLR 2021 · 154 citations
  2. Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta PosteriorRaphael Shu, Jason Lee, Hideki Nakayama, Kyunghyun ChoAAAI 2020 · 125 citations
  3. Neural Machine Translation Quality and Post-Editing PerformanceVilém Zouhar, Martin Popel, Ondrej Bojar, Ales TamchynaEMNLP 2021 · 13 citations
  4. Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine TranslationSunzhu Li, Peng Zhang, Guobing Gan, Xiuqing Lv et al.EMNLP 2022 · 3 citations
  5. Glancing Transformer for Non-Autoregressive Neural Machine TranslationLihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang et al.ACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines