mlsanityData to 7 Oct 2026

Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data

arXiv 2504.21747 ↗First posted 30 Apr 2025cs.CLcited by 0

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

Abstract (arXiv)

Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work explores ways to take advantage of such resources by directly retrieving relevant target language segments, based on a source-side query. For this, we design improved cross-lingual retrieval systems, trained with both sentence level and word-level matching objectives. In our experiments with three RANMT architectures, we assess such cross-lingual objectives in a controlled setting, reaching performances that match those of standard TM-based models. We also showcase our method on a real-world settings, using much larger monolingual and observe strong improvements over both the baseline setting and general-purpose cross-lingual retrievers.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 37 of its 73 references that are in the map. First posted on arXiv 30 Apr 2025.

Builds on

37 of 73 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison3 Apr
  2. 2023Towards Example-Based NMT with Multi-Levenshtein Transformers13 Oct
  3. 2022Neural Machine Translation with Contrastive Translation Memories6 Dec

Other references · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  8. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  9. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  10. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  11. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  12. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
22 more
  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  2. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 205
  3. 2019Levenshtein Transformercited by 197
  4. 2022In-context Examples Selection for Machine Translationcited by 172
  5. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  6. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  7. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  8. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  9. 2013A Theoretical Analysis of NDCG Type Ranking Measurescited by 119
  10. 2023SONAR: Sentence-Level Multimodal and Language-Agnostic Representationscited by 105
  11. 2018Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddingscited by 83
  12. 2019Tagged Back-Translationcited by 76
  13. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  14. 2023Adaptive Machine Translation with Large Language Modelscited by 58
  15. 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOMcited by 58
  16. 2018End-to-End Retrieval in Continuous Spacecited by 46
  17. 2019Domain, Translationese and Noise in Synthetic Data for Neural Machine Translationcited by 26
  18. 2019Using Monolingual Data in Neural Machine Translation: a Systematic Studycited by 21
  19. 2024In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translationcited by 21
  20. 2022Nearest Neighbor Non-autoregressive Text Generationcited by 7
  21. 2022Integrating Translation Memories into Non-Autoregressive Machine Translationcited by 5
  22. 2023Prompting Neural Machine Translation with Translation Memoriescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledge
  2. 2024Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems
  3. 2024Optimizing example selection for retrieval-augmented machine translation with translation memories
  4. 2022Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
  5. 2025Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
  6. 2022Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions
  7. 2023Crosslingual Retrieval Augmented In-context Learning for Bangla
  8. 2025How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting