mlsanityData to 7 Oct 2026

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

arXiv 2109.09991 ↗First posted 21 Sep 2021cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adaptation and multi-domain machine translation datasets show that even without expensive retraining, KSTER is able to achieve improvement of 1.1 to 1.5 BLEU scores over the best existing online adaptation methods. The code and trained models are released at https://github.com/jiangqn/KSTER.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

24 of 40 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  8. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  9. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  10. 2020Parameter-Efficient Transfer Learning with Diff Pruningcited by 351
  11. 2017Six Challenges for Neural Machine Translationcited by 334
  12. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 239
12 more
  1. 2020Nearest Neighbor Machine Translationcited by 209
  2. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  3. 2020On the Sentence Embeddings from Pre-trained Language Modelscited by 83
  4. 2021WhiteningBERT: An Easy Unsupervised Sentence Embedding Approachcited by 68
  5. 2018A Survey of Domain Adaptation for Neural Machine Translationcited by 64
  6. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  7. 2016One-shot Learning with Memory-Augmented Neural Networkscited by 60
  8. 2021Learning Language Specific Sub-network for Multilingual Machine Translationcited by 48
  9. 2019Joey NMT: A Minimalist NMT Toolkit for Novicescited by 39
  10. 2021Counter-Interference Adapter for Multilingual Machine Translationcited by 39
  11. 2019Non-Parametric Adaptation for Neural Machine Translationcited by 34
  12. 2018Compact Personalized Models for Neural Machine Translationcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 7; 2024: 6; 2025: 1; 2026: 1.

25 papers.

Sort:

By area:

  1. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  2. 2022Efficient Cluster-Based k-Nearest-Neighbor Machine Translationcited by 24
  3. 2023Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Modelscited by 23
  4. 2022Chunk-based Nearest Neighbor Machine Translationcited by 21
  5. 2022Towards Robust k-Nearest-Neighbor Machine Translationcited by 15
  6. 2023Simple and Scalable Nearest Neighbor Machine Translationcited by 12
  7. 2022Efficient Machine Translation Domain Adaptationcited by 7
  8. 2022What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptationcited by 7
  9. 2023Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarizationcited by 6
  10. 2024ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotationcited by 6
  11. 2024NNOSE: Nearest Neighbor Occupational Skill Extractioncited by 5
  12. 2022Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translationcited by 4
13 more
  1. 2022Analogical Math Word Problems Solving with Enhanced Problem-Solution Associationcited by 4
  2. 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generationcited by 4
  3. 2023kNN-BOX: A Unified Framework for Nearest Neighbor Generationcited by 3
  4. 2022Better Datastore, Better Translation: Generating Datastores from Pre-Trained Models for Nearest Neural Machine Translationcited by 2
  5. 2024Generating Diverse Translation with Perturbed kNN-MTcited by 2
  6. 2022An Empirical Study of Retrieval-enhanced Graph Neural Networkscited by 1
  7. 2023N-Gram Nearest Neighbor Machine Translationcited by 1
  8. 2023Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layercited by 1
  9. 2025Long-Tail Crisis in Nearest Neighbor Language Modelscited by 1
  10. 2023Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translationcited by 0
  11. 2024Simply Trainable Nearest Neighbour Machine Translation with GPU Inferencecited by 0
  12. 2024Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximizationcited by 0
  13. 2026RASST: Retrieval-Augmented Simultaneous Speech Translationcited by 0