# Optimizing example selection for retrieval-augmented machine translation with translation memories

arXiv: https://arxiv.org/abs/2405.15070 · HTML: https://mlsanity.com/paper/2405.15070/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 23 May 2024.

## Placed in

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

## Builds on (most cited first, 3 of 3)

- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models](https://mlsanity.com/paper/2305.03573/) (2023)
- [Nearest Neighbor Non-autoregressive Text Generation](https://mlsanity.com/paper/2208.12496/) (2022)

## Abstract (arXiv)

Retrieval-augmented machine translation leverages examples from a translation memory by retrieving similar instances. These examples are used to condition the predictions of a neural decoder. We aim to improve the upstream retrieval step and consider a fixed downstream edit-based model: the multi-Levenshtein Transformer. The task consists of finding a set of examples that maximizes the overall coverage of the source sentence. To this end, we rely on the theory of submodular functions and explore new algorithms to optimize this coverage. We evaluate the resulting performance gains for the machine translation task.