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.

检索增强机器翻译通过检索类似实例的翻译记忆，以条件化神经解码器的预测。我们的目标是改进上游检索步骤，并考虑固定下游基于编辑的模型：多 Levenshtein Transformer。该任务是找到一组能够最大化源句子整体覆盖率的例子。为此，我们依赖于次模函数的理论，并探索优化这种覆盖的新算法。我们评估这些性能改进对机器翻译任务的影响。

通过利用翻译记忆进行检索增强机器翻译的优化示例选择

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

Retrieval-Augmented Machine Translation (RAMT) is attracting growing
attention. This is because RAMT not only improves translation metrics, but is
also assumed to implement some form of domain adaptation. In this contribution,
we study another salient trait of RAMT, its ability to make translation
decisions more transparent by allowing users to go back to examples that
contributed to these decisions.
For this, we propose a novel architecture aiming to increase this
transparency. This model adapts a retrieval-augmented version of the
Levenshtein Transformer and makes it amenable to simultaneously edit multiple
fuzzy matches found in memory. We discuss how to perform training and inference
in this model, based on multi-way alignment algorithms and imitation learning.
Our experiments show that editing several examples positively impacts
translation scores, notably increasing the number of target spans that are
copied from existing instances.

提出了一种新颖的基于检索增强的 Levenshtein Transformer 架构，旨在提高 Retrieval-Augmented Machine Translation 的透明度，并通过编辑多个模糊匹配的示例来改善翻译得分。