# Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

arXiv: https://arxiv.org/abs/2404.02835 · HTML: https://mlsanity.com/paper/2404.02835/

## Key facts

- Cited by 7 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 22 of its 46 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 22 of 22)

- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2010.00710/) (2020)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [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)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [Guiding Neural Machine Translation with Retrieved Translation Pieces](https://mlsanity.com/paper/1804.02559/) (2018)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM](https://mlsanity.com/paper/2303.01911/) (2023)
- [Coverage-based Example Selection for In-Context Learning](https://mlsanity.com/paper/2305.14907/) (2023)
- [Chunk-based Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2205.12230/) (2022)
- [Augmenting Large Language Model Translators via Translation Memories](https://mlsanity.com/paper/2305.17367/) (2023)
- [Neural Machine Translation with Contrastive Translation Memories](https://mlsanity.com/paper/2212.03140/) (2022)
- [CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation](https://mlsanity.com/paper/2305.14105/) (2023)
- [Nearest Neighbor Non-autoregressive Text Generation](https://mlsanity.com/paper/2208.12496/) (2022)
- [Integrating Translation Memories into Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2210.06020/) (2022)
- [Towards Example-Based NMT with Multi-Levenshtein Transformers](https://mlsanity.com/paper/2310.08967/) (2023)

## Built on by (most cited first, 7 of 7)

- [In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation](https://mlsanity.com/paper/2408.00397/) (2024)
- [Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation](https://mlsanity.com/paper/2503.04554/) (2025)
- [An Interdisciplinary Approach to Human-Centered Machine Translation](https://mlsanity.com/paper/2506.13468/) (2025)
- [ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning](https://mlsanity.com/paper/2507.07306/) (2025)
- [Exploring In-context Example Generation for Machine Translation](https://mlsanity.com/paper/2506.00507/) (2025)
- [Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data](https://mlsanity.com/paper/2504.21747/) (2025)
- [TULUN: Transparent and Adaptable Low-resource Machine Translation](https://mlsanity.com/paper/2505.18683/) (2025)

## Abstract (arXiv)

Retrieval-Augmented Neural Machine Translation (RAMT) architectures retrieve examples from memory to guide the generation process. While most works in this trend explore new ways to exploit the retrieved examples, the upstream retrieval step is mostly unexplored. In this paper, we study the effect of varying retrieval methods for several translation architectures, to better understand the interplay between these two processes. We conduct experiments in two language pairs in a multi-domain setting and consider several downstream architectures based on a standard autoregressive model, an edit-based model, and a large language model with in-context learning. Our experiments show that the choice of the retrieval technique impacts the translation scores, with variance across architectures. We also discuss the effects of increasing the number and diversity of examples, which are mostly positive across the board.