@inproceedings{bouthors-etal-2024-retrieving,
title = "Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison",
author = "Bouthors, Maxime and
Crego, Josep and
Yvon, Fran{\c{c}}ois",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.190/",
doi = "10.18653/v1/2024.findings-naacl.190",
pages = "3022--3039",
abstract = "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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bouthors-etal-2024-retrieving">
<titleInfo>
<title>Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Bouthors</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">bouthors-etal-2024-retrieving</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.190</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.190/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3022</start>
<end>3039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison
%A Bouthors, Maxime
%A Crego, Josep
%A Yvon, François
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F bouthors-etal-2024-retrieving
%X 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.
%R 10.18653/v1/2024.findings-naacl.190
%U https://aclanthology.org/2024.findings-naacl.190/
%U https://doi.org/10.18653/v1/2024.findings-naacl.190
%P 3022-3039
Markdown (Informal)
[Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison](https://aclanthology.org/2024.findings-naacl.190/) (Bouthors et al., Findings 2024)
ACL