@inproceedings{garcia-gilabert-etal-2025-mt,
title = "{MT}-{LENS}: An all-in-one Toolkit for Better Machine Translation Evaluation",
author = "Garc{\'i}a Gilabert, Javier and
Escolano, Carlos and
Mash, Audrey and
Liao, Xixian and
Melero, Maite",
editor = "Dziri, Nouha and
Ren, Sean (Xiang) and
Diao, Shizhe",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-demo.6/",
doi = "10.18653/v1/2025.naacl-demo.6",
pages = "51--60",
ISBN = "979-8-89176-191-9",
abstract = "We introduce MT-Lens, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-Lens addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluation metrics. It also offers a user-friendly platform to compare systems and analyze translations with interactive visualizations. MT-Lens aims to broaden access to evaluation strategies that go beyond traditional translation quality evaluation, enabling researchers and engineers to better understand the performance of a NMT model and also easily measure system{'}s biases."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-gilabert-etal-2025-mt">
<titleInfo>
<title>MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">García Gilabert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Escolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Audrey</namePart>
<namePart type="family">Mash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xixian</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="given">(Xiang)</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhe</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-191-9</identifier>
</relatedItem>
<abstract>We introduce MT-Lens, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-Lens addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluation metrics. It also offers a user-friendly platform to compare systems and analyze translations with interactive visualizations. MT-Lens aims to broaden access to evaluation strategies that go beyond traditional translation quality evaluation, enabling researchers and engineers to better understand the performance of a NMT model and also easily measure system’s biases.</abstract>
<identifier type="citekey">garcia-gilabert-etal-2025-mt</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-demo.6</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-demo.6/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>51</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
%A García Gilabert, Javier
%A Escolano, Carlos
%A Mash, Audrey
%A Liao, Xixian
%A Melero, Maite
%Y Dziri, Nouha
%Y Ren, Sean (Xiang)
%Y Diao, Shizhe
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-191-9
%F garcia-gilabert-etal-2025-mt
%X We introduce MT-Lens, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-Lens addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluation metrics. It also offers a user-friendly platform to compare systems and analyze translations with interactive visualizations. MT-Lens aims to broaden access to evaluation strategies that go beyond traditional translation quality evaluation, enabling researchers and engineers to better understand the performance of a NMT model and also easily measure system’s biases.
%R 10.18653/v1/2025.naacl-demo.6
%U https://aclanthology.org/2025.naacl-demo.6/
%U https://doi.org/10.18653/v1/2025.naacl-demo.6
%P 51-60
Markdown (Informal)
[MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation](https://aclanthology.org/2025.naacl-demo.6/) (García Gilabert et al., NAACL 2025)
ACL
- Javier García Gilabert, Carlos Escolano, Audrey Mash, Xixian Liao, and Maite Melero. 2025. MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations), pages 51–60, Albuquerque, New Mexico. Association for Computational Linguistics.