mlsanityData to 7 Oct 2026

Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions

arXiv 2210.05047 ↗First posted 10 Oct 2022cs.CLcited by 7

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. We build on the idea of Retrieval Augmented Translation (RAT) where top-k in-domain fuzzy matches are found for the source sentence, and target-language translations of those fuzzy-matched sentences are provided to the translation model at inference time. We propose a novel architecture to control interactions between a source sentence and the top-k fuzzy target-language matches, and compare it to architectures from prior work. We conduct experiments in two language pairs (En-De and En-Fr) by training models on WMT data and testing them with five and seven multi-domain datasets, respectively. Our approach consistently outperforms the alternative architectures, improving BLEU across language pair, domain, and number k of fuzzy matches.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 37 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

17 of 37 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2017Six Challenges for Neural Machine Translationcited by 334
  6. 2020Nearest Neighbor Machine Translationcited by 209
  7. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  8. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  9. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  10. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  11. 2021Adaptive Nearest Neighbor Machine Translationcited by 58
  12. 2019compare-mt: A Tool for Holistic Comparison of Language Generation Systemscited by 43
5 more
  1. 2016Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptationcited by 38
  2. 2021Fast Nearest Neighbor Machine Translationcited by 37
  3. 2016Fast Domain Adaptation for Neural Machine Translationcited by 28
  4. 2020The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020cited by 16
  5. 2017Search Engine Guided Non-Parametric Neural Machine Translationcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 4.

7 papers.

  1. 2024Understanding Retrieval Robustness for Retrieval-Augmented Image Captioningcited by 9
  2. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledgecited by 8
  3. 2023Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applicationscited by 7
  4. 2024Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translationcited by 3
  5. 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
  6. 2023Towards Example-Based NMT with Multi-Levenshtein Transformerscited by 2
  7. 2023Rethinking Translation Memory Augmented Neural Machine Translationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
  2. 2025Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
  3. 2024Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison
  4. 2024Optimizing example selection for retrieval-augmented machine translation with translation memories
  5. 2022Efficient Machine Translation Domain Adaptation
  6. 2022kNN-Prompt: Nearest Neighbor Zero-Shot Inference
  7. 2022Neural Machine Translation with Contrastive Translation Memories
  8. 2024Reliable, Adaptable, and Attributable Language Models with Retrieval