mlsanityData to 7 Oct 2026

Faster Nearest Neighbor Machine Translation

arXiv 2112.08152 ↗First posted 15 Dec 2021cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

kNN based neural machine translation (kNN-MT) has achieved state-of-the-art results in a variety of MT tasks. One significant shortcoming of kNN-MT lies in its inefficiency in identifying the k nearest neighbors of the query representation from the entire datastore, which is prohibitively time-intensive when the datastore size is large. In this work, we propose Faster kNN-MT to address this issue. The core idea of Faster kNN-MT is to use a hierarchical clustering strategy to approximate the distance between the query and a data point in the datastore, which is decomposed into two parts: the distance between the query and the center of the cluster that the data point belongs to, and the distance between the data point and the cluster center. We propose practical ways to compute these two parts in a significantly faster manner. Through extensive experiments on different MT benchmarks, we show that Faster kNN-MT is faster than Fast kNN-MT citepmeng2021fast and only slightly (1.2 times) slower than its vanilla counterpart while preserving model performance as kNN-MT. Faster kNN-MT enables the deployment of kNN-MT models on real-world MT services.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 49 references that are in the map. First posted on arXiv 15 Dec 2021.

Builds on

39 of 49 references.

References · 39

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  9. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  10. 2020On Layer Normalization in the Transformer Architecturecited by 906
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
27 more
  1. 2021Random Feature Attentioncited by 350
  2. 2017Six Challenges for Neural Machine Translationcited by 334
  3. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  4. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  5. 2020Understanding the Difficulty of Training Transformerscited by 210
  6. 2020Nearest Neighbor Machine Translationcited by 209
  7. 2020Synthesizer: Rethinking Self-Attention in Transformer Modelscited by 204
  8. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  9. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  10. 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
  11. 2020Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translationcited by 104
  12. 2021Finetuning Pretrained Transformers into RNNscited by 94
  13. 2020Pre-training via Paraphrasingcited by 92
  14. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  15. 2016Improving Neural Language Models with a Continuous Cachecited by 81
  16. 2021BertGCN: Transductive Text Classification by Combining GCN and BERTcited by 74
  17. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  18. 2020Augmenting Transformers with KNN-Based Composite Memory for Dialoguecited by 53
  19. 2017Learning to Remember Translation History with a Continuous Cachecited by 39
  20. 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
  21. 2021Fast Nearest Neighbor Machine Translationcited by 37
  22. 2016Mutual Information and Diverse Decoding Improve Neural Machine Translationcited by 35
  23. 2019Non-Parametric Adaptation for Neural Machine Translationcited by 34
  24. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
  25. 2021GNN-LM: Language Modeling based on Global Contexts via GNNcited by 27
  26. 2020SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connectioncited by 13
  27. 2020Time-aware Large Kernel Convolutionscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 2.

8 papers.

  1. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  2. 2022Chunk-based Nearest Neighbor Machine Translationcited by 21
  3. 2022Nearest Neighbor Knowledge Distillation for Neural Machine Translationcited by 10
  4. 2022kNN-NER: Named Entity Recognition with Nearest Neighbor Searchcited by 6
  5. 2022GNN-SL: Sequence Labeling Based on Nearest Examples via GNNcited by 3
  6. 2022Nearest Neighbor Language Models for Stylistic Controllable Generationcited by 2
  7. 2023Prompting Neural Machine Translation with Translation Memoriescited by 2
  8. 2023Rethinking Translation Memory Augmented Neural Machine Translationcited by 1