@inproceedings{cettolo-etal-2024-magnet,
title = "{MAGNET} - {MA}chines {G}e{NE}rating Translations: A {CALAMITA} Challenge",
author = "Cettolo, Mauro and
Piergentili, Andrea and
Papi, Sara and
Gaido, Marco and
Negri, Matteo and
Bentivogli, Luisa",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.120/",
pages = "1089--1093",
ISBN = "979-12-210-7060-6",
abstract = "We propose MAGNET - MAchines GeNErating Translations, a CALAMITA Challenge which aims at testing the ability of large language models (LLMs) in the hot topic of automatic translation, focusing on Italian and English (in both directions) to overcome the marginality with which Italian is considered by the machine translation community. We propose a benchmark composed of two portions with different distribution policies (one free to use, the other not discloseable), allowing to handle data contamination issues. The publicly available section of the benchmark is distributed on Hugging Face, whereas in this report we describe the details of our challenge, including the prompt formats to be used. Additionally, we report the performance of five models, including a LLM and different sized translation models, in terms of four evaluation metrics, whose scores allow an overall evaluation of the quality of the automatically generated translations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cettolo-etal-2024-magnet">
<titleInfo>
<title>MAGNET - MAchines GeNErating Translations: A CALAMITA Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Piergentili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>We propose MAGNET - MAchines GeNErating Translations, a CALAMITA Challenge which aims at testing the ability of large language models (LLMs) in the hot topic of automatic translation, focusing on Italian and English (in both directions) to overcome the marginality with which Italian is considered by the machine translation community. We propose a benchmark composed of two portions with different distribution policies (one free to use, the other not discloseable), allowing to handle data contamination issues. The publicly available section of the benchmark is distributed on Hugging Face, whereas in this report we describe the details of our challenge, including the prompt formats to be used. Additionally, we report the performance of five models, including a LLM and different sized translation models, in terms of four evaluation metrics, whose scores allow an overall evaluation of the quality of the automatically generated translations.</abstract>
<identifier type="citekey">cettolo-etal-2024-magnet</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.120/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>1089</start>
<end>1093</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAGNET - MAchines GeNErating Translations: A CALAMITA Challenge
%A Cettolo, Mauro
%A Piergentili, Andrea
%A Papi, Sara
%A Gaido, Marco
%A Negri, Matteo
%A Bentivogli, Luisa
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F cettolo-etal-2024-magnet
%X We propose MAGNET - MAchines GeNErating Translations, a CALAMITA Challenge which aims at testing the ability of large language models (LLMs) in the hot topic of automatic translation, focusing on Italian and English (in both directions) to overcome the marginality with which Italian is considered by the machine translation community. We propose a benchmark composed of two portions with different distribution policies (one free to use, the other not discloseable), allowing to handle data contamination issues. The publicly available section of the benchmark is distributed on Hugging Face, whereas in this report we describe the details of our challenge, including the prompt formats to be used. Additionally, we report the performance of five models, including a LLM and different sized translation models, in terms of four evaluation metrics, whose scores allow an overall evaluation of the quality of the automatically generated translations.
%U https://aclanthology.org/2024.clicit-1.120/
%P 1089-1093
Markdown (Informal)
[MAGNET - MAchines GeNErating Translations: A CALAMITA Challenge](https://aclanthology.org/2024.clicit-1.120/) (Cettolo et al., CLiC-it 2024)
ACL