Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
On the map: Retrieval-augmented generation → Generation and context integration
Abstract (arXiv)
Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved from a translation memory (TM). However, these studies all operate under the assumption that the TMs available at test time are highly relevant to the testset. We demonstrate that for existing retrieval augmented translation methods, using a TM with a domain mismatch to the test set can result in substantially worse performance compared to not using a TM at all. We propose a simple method to expose fuzzy-match NMT systems during training and show that it results in a system that is much more tolerant (regaining up to 5.8 BLEU) to inference with TMs with domain mismatch. Also, the model is still competitive to the baseline when fed with suggestions from relevant TMs.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 36 references that are in the map. First posted on arXiv 11 Oct 2022.
Builds on
20 of 36 references.
References · 20
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
- 2017Six Challenges for Neural Machine Translationcited by 335
- 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 306
- 2020Nearest Neighbor Machine Translationcited by 209
- 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
- 2022A Survey on Retrieval-Augmented Text Generationcited by 158
- 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
- 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
8 more
- 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
- 2021Adaptive Nearest Neighbor Machine Translationcited by 58
- 2019compare-mt: A Tool for Holistic Comparison of Language Generation Systemscited by 43
- 2016Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptationcited by 40
- 2021Fast Nearest Neighbor Machine Translationcited by 37
- 2016Fast Domain Adaptation for Neural Machine Translationcited by 28
- 2017Search Engine Guided Non-Parametric Neural Machine Translationcited by 10
- 2019Domain Adaptive Inference for Neural Machine Translationcited by 10
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2022Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions
- 2023Towards Example-Based NMT with Multi-Levenshtein Transformers
- 2022Neural Machine Translation with Contrastive Translation Memories
- 2024Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison
- 2025Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
- 2024Optimizing example selection for retrieval-augmented machine translation with translation memories
- 2025Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
- 2025Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation