@inproceedings{falcao-etal-2024-comet,
title = "{COMET} for Low-Resource Machine Translation Evaluation: A Case Study of {E}nglish-{M}altese and {S}panish-{B}asque",
author = "Falc{\~a}o, J{\'u}lia and
Borg, Claudia and
Aranberri, Nora and
Abela, Kurt",
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.315",
pages = "3553--3565",
abstract = "Trainable metrics for machine translation evaluation have been scoring the highest correlations with human judgements in the latest meta-evaluations, outperforming traditional lexical overlap metrics such as BLEU, which is still widely used despite its well-known shortcomings. In this work we look at COMET, a prominent neural evaluation system proposed in 2020, to analyze the extent of its language support restrictions, and to investigate strategies to extend this support to new, under-resourced languages. Our case study focuses on English-Maltese and Spanish-Basque. We run a crowd-based evaluation campaign to collect direct assessments and use the annotated dataset to evaluate COMET-22, further fine-tune it, and to train COMET models from scratch for the two language pairs. Our analysis suggests that COMET{'}s performance can be improved with fine-tuning, and that COMET can be highly susceptible to the distribution of scores in the training data, which especially impacts low-resource scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="falcao-etal-2024-comet">
<titleInfo>
<title>COMET for Low-Resource Machine Translation Evaluation: A Case Study of English-Maltese and Spanish-Basque</title>
</titleInfo>
<name type="personal">
<namePart type="given">Júlia</namePart>
<namePart type="family">Falcão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Abela</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>Trainable metrics for machine translation evaluation have been scoring the highest correlations with human judgements in the latest meta-evaluations, outperforming traditional lexical overlap metrics such as BLEU, which is still widely used despite its well-known shortcomings. In this work we look at COMET, a prominent neural evaluation system proposed in 2020, to analyze the extent of its language support restrictions, and to investigate strategies to extend this support to new, under-resourced languages. Our case study focuses on English-Maltese and Spanish-Basque. We run a crowd-based evaluation campaign to collect direct assessments and use the annotated dataset to evaluate COMET-22, further fine-tune it, and to train COMET models from scratch for the two language pairs. Our analysis suggests that COMET’s performance can be improved with fine-tuning, and that COMET can be highly susceptible to the distribution of scores in the training data, which especially impacts low-resource scenarios.</abstract>
<identifier type="citekey">falcao-etal-2024-comet</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.315</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3553</start>
<end>3565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COMET for Low-Resource Machine Translation Evaluation: A Case Study of English-Maltese and Spanish-Basque
%A Falcão, Júlia
%A Borg, Claudia
%A Aranberri, Nora
%A Abela, Kurt
%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 falcao-etal-2024-comet
%X Trainable metrics for machine translation evaluation have been scoring the highest correlations with human judgements in the latest meta-evaluations, outperforming traditional lexical overlap metrics such as BLEU, which is still widely used despite its well-known shortcomings. In this work we look at COMET, a prominent neural evaluation system proposed in 2020, to analyze the extent of its language support restrictions, and to investigate strategies to extend this support to new, under-resourced languages. Our case study focuses on English-Maltese and Spanish-Basque. We run a crowd-based evaluation campaign to collect direct assessments and use the annotated dataset to evaluate COMET-22, further fine-tune it, and to train COMET models from scratch for the two language pairs. Our analysis suggests that COMET’s performance can be improved with fine-tuning, and that COMET can be highly susceptible to the distribution of scores in the training data, which especially impacts low-resource scenarios.
%U https://aclanthology.org/2024.lrec-main.315
%P 3553-3565
Markdown (Informal)
[COMET for Low-Resource Machine Translation Evaluation: A Case Study of English-Maltese and Spanish-Basque](https://aclanthology.org/2024.lrec-main.315) (Falcão et al., LREC-COLING 2024)
ACL