@inproceedings{martins-etal-2023-empirical,
title = "Empirical Assessment of k{NN}-{MT} for Real-World Translation Scenarios",
author = "Martins, Pedro Henrique and
Alves, Jo{\~a}o and
Vaz, T{\^a}nia and
Gon{\c{c}}alves, Madalena and
Silva, Beatriz and
Buchicchio, Marianna and
de Souza, Jos{\'e} G. C. and
Martins, Andr{\'e} F. T.",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.12/",
pages = "115--124",
abstract = "This paper aims to investigate the effectiveness of the k-Nearest Neighbor Machine Translation model (kNN-MT) in real-world scenarios. kNN-MT is a retrieval-augmented framework that combines the advantages of parametric models with non-parametric datastores built using a set of parallel sentences. Previous studies have primarily focused on evaluating the model using only the BLEU metric and have not tested kNN-MT in real world scenarios. Our study aims to fill this gap by conducting a comprehensive analysis on various datasets comprising different language pairs and different domains, using multiple automatic metrics and expert evaluated Multidimensional Quality Metrics (MQM). We compare kNN-MT with two alternate strategies: fine-tuning all the model parameters and adapter-based finetuning. Finally, we analyze the effect of the datastore size on translation quality, and we examine the number of entries necessary to bootstrap and configure the index."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martins-etal-2023-empirical">
<titleInfo>
<title>Empirical Assessment of kNN-MT for Real-World Translation Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tânia</namePart>
<namePart type="family">Vaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madalena</namePart>
<namePart type="family">Gonçalves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatriz</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Buchicchio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">G</namePart>
<namePart type="given">C</namePart>
<namePart type="family">de Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">F</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper aims to investigate the effectiveness of the k-Nearest Neighbor Machine Translation model (kNN-MT) in real-world scenarios. kNN-MT is a retrieval-augmented framework that combines the advantages of parametric models with non-parametric datastores built using a set of parallel sentences. Previous studies have primarily focused on evaluating the model using only the BLEU metric and have not tested kNN-MT in real world scenarios. Our study aims to fill this gap by conducting a comprehensive analysis on various datasets comprising different language pairs and different domains, using multiple automatic metrics and expert evaluated Multidimensional Quality Metrics (MQM). We compare kNN-MT with two alternate strategies: fine-tuning all the model parameters and adapter-based finetuning. Finally, we analyze the effect of the datastore size on translation quality, and we examine the number of entries necessary to bootstrap and configure the index.</abstract>
<identifier type="citekey">martins-etal-2023-empirical</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.12/</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>115</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empirical Assessment of kNN-MT for Real-World Translation Scenarios
%A Martins, Pedro Henrique
%A Alves, João
%A Vaz, Tânia
%A Gonçalves, Madalena
%A Silva, Beatriz
%A Buchicchio, Marianna
%A de Souza, José G. C.
%A Martins, André F. T.
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F martins-etal-2023-empirical
%X This paper aims to investigate the effectiveness of the k-Nearest Neighbor Machine Translation model (kNN-MT) in real-world scenarios. kNN-MT is a retrieval-augmented framework that combines the advantages of parametric models with non-parametric datastores built using a set of parallel sentences. Previous studies have primarily focused on evaluating the model using only the BLEU metric and have not tested kNN-MT in real world scenarios. Our study aims to fill this gap by conducting a comprehensive analysis on various datasets comprising different language pairs and different domains, using multiple automatic metrics and expert evaluated Multidimensional Quality Metrics (MQM). We compare kNN-MT with two alternate strategies: fine-tuning all the model parameters and adapter-based finetuning. Finally, we analyze the effect of the datastore size on translation quality, and we examine the number of entries necessary to bootstrap and configure the index.
%U https://aclanthology.org/2023.eamt-1.12/
%P 115-124
Markdown (Informal)
[Empirical Assessment of kNN-MT for Real-World Translation Scenarios](https://aclanthology.org/2023.eamt-1.12/) (Martins et al., EAMT 2023)
ACL
- Pedro Henrique Martins, João Alves, Tânia Vaz, Madalena Gonçalves, Beatriz Silva, Marianna Buchicchio, José G. C. de Souza, and André F. T. Martins. 2023. Empirical Assessment of kNN-MT for Real-World Translation Scenarios. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 115–124, Tampere, Finland. European Association for Machine Translation.