# Nearest Neighbor Machine Translation

arXiv: https://arxiv.org/abs/2010.00710 · HTML: https://mlsanity.com/paper/2010.00710/

## Key facts

- Cited by 209 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 30 of 209)

- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [Training Language Models with Memory Augmentation](https://mlsanity.com/paper/2205.12674/) (2022)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [Adaptive Semiparametric Language Models](https://mlsanity.com/paper/2102.02557/) (2021)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [Efficient Methods for Natural Language Processing: A Survey](https://mlsanity.com/paper/2209.00099/) (2022)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [Retrieval-Augmented Generation for Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.13193/) (2024)
- [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://mlsanity.com/paper/2310.05002/) (2023)
- [Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models](https://mlsanity.com/paper/2207.13038/) (2022)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval](https://mlsanity.com/paper/2201.12431/) (2022)
- [Adaptive Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2105.13022/) (2021)
- [Personalized Federated Learning through Local Memorization](https://mlsanity.com/paper/2111.09360/) (2021)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)

## Abstract (arXiv)

We introduce k-nearest-neighbor machine translation (kNN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. kNN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results -- without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, kNN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.