mlsanityData to 7 Oct 2026

Efficient Inference for Multilingual Neural Machine Translation

arXiv 2109.06679 ↗First posted 14 Sep 2021cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at inference without degrading its quality. We experiment with several "light decoder" architectures in two 20-language multi-parallel settings: small-scale on TED Talks and large-scale on ParaCrawl. Our experiments demonstrate that combining a shallow decoder with vocabulary filtering leads to more than twice faster inference with no loss in translation quality. We validate our findings with BLEU and chrF (on 380 language pairs), robustness evaluation and human evaluation.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

29 of 44 references.

References · 29

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  3. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  4. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  5. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  6. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  7. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  8. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  9. 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 253
  10. 2019Massively Multilingual Neural Machine Translationcited by 246
  11. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 239
  12. 2020Understanding the Difficulty of Training Transformerscited by 210
17 more
  1. 2018When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?cited by 125
  2. 2020Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translationcited by 104
  3. 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 101
  4. 2021Finetuning Pretrained Transformers into RNNscited by 94
  5. 2021Do Transformer Modifications Transfer Across Implementations and Applications?cited by 87
  6. 2020Evaluating Robustness to Input Perturbations for Neural Machine Translationcited by 36
  7. 2020Shallow-to-Deep Training for Neural Machine Translationcited by 36
  8. 2017Compressing Word Embeddings via Deep Compositional Code Learningcited by 34
  9. 2021When Attention Meets Fast Recurrence: Training Language Models with Reduced Computecited by 34
  10. 2019A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translationcited by 30
  11. 2020Complete Multilingual Neural Machine Translationcited by 30
  12. 2021Language Tags Matter for Zero-Shot Neural Machine Translationcited by 29
  13. 2020Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoderscited by 23
  14. 2019Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Taskcited by 22
  15. 2021An Efficient Transformer Decoder with Compressed Sub-layerscited by 10
  16. 2020Efficient Inference For Neural Machine Translationcited by 7
  17. 2020Revisiting Modularized Multilingual NMT to Meet Industrial Demandscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 2.

10 papers.

  1. 2023Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfercited by 22
  2. 2022SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languagescited by 16
  3. 2021Continual Learning in Multilingual NMT via Language-Specific Embeddingscited by 12
  4. 2022Understanding and Mitigating the Uncertainty in Zero-Shot Translationcited by 9
  5. 2023NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Trackcited by 9
  6. 2023CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Codecited by 9
  7. 2024Accelerating Multilingual Language Model for Excessively Tokenized Languagescited by 8
  8. 2022When does Parameter-Efficient Transfer Learning Work for Machine Translation?cited by 7
  9. 2022The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translationcited by 3
  10. 2024Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translationcited by 1