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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bouthors, Maxime, Crego, Josep, Yvon, François
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910458641907712
author Bouthors, Maxime
Crego, Josep
Yvon, François
author_facet Bouthors, Maxime
Crego, Josep
Yvon, François
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15070
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Optimizing example selection for retrieval-augmented machine translation with translation memories
Bouthors, Maxime
Crego, Josep
Yvon, François
Computation and Language
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.
title Optimizing example selection for retrieval-augmented machine translation with translation memories
topic Computation and Language
url https://arxiv.org/abs/2405.15070