@inproceedings{jon-bojar-2024-gaatme,
title = "{GAATME}: A Genetic Algorithm for Adversarial Translation Metrics Evaluation",
author = "Jon, Josef and
Bojar, Ond{\v{r}}ej",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.668/",
pages = "7562--7569",
abstract = "Building on a recent method for decoding translation candidates from a Machine Translation (MT) model via a genetic algorithm, we modify it to generate adversarial translations to test and challenge MT evaluation metrics. The produced translations score very well in an arbitrary MT evaluation metric selected beforehand, despite containing serious, deliberately introduced errors. The method can be used to create adversarial test sets to analyze the biases and shortcomings of the metrics. We publish various such test sets for the Czech to English language pair, as well as the code to convert any parallel data into a similar adversarial test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jon-bojar-2024-gaatme">
<titleInfo>
<title>GAATME: A Genetic Algorithm for Adversarial Translation Metrics Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Jon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building on a recent method for decoding translation candidates from a Machine Translation (MT) model via a genetic algorithm, we modify it to generate adversarial translations to test and challenge MT evaluation metrics. The produced translations score very well in an arbitrary MT evaluation metric selected beforehand, despite containing serious, deliberately introduced errors. The method can be used to create adversarial test sets to analyze the biases and shortcomings of the metrics. We publish various such test sets for the Czech to English language pair, as well as the code to convert any parallel data into a similar adversarial test set.</abstract>
<identifier type="citekey">jon-bojar-2024-gaatme</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.668/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7562</start>
<end>7569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GAATME: A Genetic Algorithm for Adversarial Translation Metrics Evaluation
%A Jon, Josef
%A Bojar, Ondřej
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F jon-bojar-2024-gaatme
%X Building on a recent method for decoding translation candidates from a Machine Translation (MT) model via a genetic algorithm, we modify it to generate adversarial translations to test and challenge MT evaluation metrics. The produced translations score very well in an arbitrary MT evaluation metric selected beforehand, despite containing serious, deliberately introduced errors. The method can be used to create adversarial test sets to analyze the biases and shortcomings of the metrics. We publish various such test sets for the Czech to English language pair, as well as the code to convert any parallel data into a similar adversarial test set.
%U https://aclanthology.org/2024.lrec-main.668/
%P 7562-7569
Markdown (Informal)
[GAATME: A Genetic Algorithm for Adversarial Translation Metrics Evaluation](https://aclanthology.org/2024.lrec-main.668/) (Jon & Bojar, LREC-COLING 2024)
ACL