@inproceedings{takahashi-etal-2021-multilingual,
title = "Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for {WMT} 2021 Metrics Task",
author = "Takahashi, Kosuke and
Ishibashi, Yoichi and
Sudoh, Katsuhito and
Nakamura, Satoshi",
editor = "Barrault, Loic and
Bojar, Ondrej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-jussa, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Freitag, Markus and
Graham, Yvette and
Grundkiewicz, Roman and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Kocmi, Tom and
Martins, Andre and
Morishita, Makoto and
Monz, Christof",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.113/",
pages = "1049--1052",
abstract = "This paper describes our submission to the WMT2021 shared metrics task. Our metric is operative to segment-level and system-level translations. Our belief toward a better metric is to detect a significant error that cannot be missed in the real practice cases of evaluation. For that reason, we used pseudo-negative examples in which attributes of some words are transferred to the reversed attribute words, and we build evaluation models to handle such serious mistakes of translations. We fine-tune a multilingual largely pre-trained model on the provided corpus of past years' metric task and fine-tune again further on the synthetic negative examples that are derived from the same fine-tune corpus. From the evaluation results of the WMT21`s development corpus, fine-tuning on the pseudo-negatives using WMT15-17 and WMT18-20 metric corpus achieved a better Pearson`s correlation score than the one fine-tuned without negative examples. Our submitted models,hyp+src{\_}hyp+ref and hyp+src{\_}hyp+ref.negative, are the plain model using WMT18-20 and the one additionally fine-tuned on negative samples, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takahashi-etal-2021-multilingual">
<titleInfo>
<title>Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for WMT 2021 Metrics Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoichi</namePart>
<namePart type="family">Ishibashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Grundkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our submission to the WMT2021 shared metrics task. Our metric is operative to segment-level and system-level translations. Our belief toward a better metric is to detect a significant error that cannot be missed in the real practice cases of evaluation. For that reason, we used pseudo-negative examples in which attributes of some words are transferred to the reversed attribute words, and we build evaluation models to handle such serious mistakes of translations. We fine-tune a multilingual largely pre-trained model on the provided corpus of past years’ metric task and fine-tune again further on the synthetic negative examples that are derived from the same fine-tune corpus. From the evaluation results of the WMT21‘s development corpus, fine-tuning on the pseudo-negatives using WMT15-17 and WMT18-20 metric corpus achieved a better Pearson‘s correlation score than the one fine-tuned without negative examples. Our submitted models,hyp+src_hyp+ref and hyp+src_hyp+ref.negative, are the plain model using WMT18-20 and the one additionally fine-tuned on negative samples, respectively.</abstract>
<identifier type="citekey">takahashi-etal-2021-multilingual</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.113/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1049</start>
<end>1052</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for WMT 2021 Metrics Task
%A Takahashi, Kosuke
%A Ishibashi, Yoichi
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Barrault, Loic
%Y Bojar, Ondrej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussa, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Freitag, Markus
%Y Graham, Yvette
%Y Grundkiewicz, Roman
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Kocmi, Tom
%Y Martins, Andre
%Y Morishita, Makoto
%Y Monz, Christof
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F takahashi-etal-2021-multilingual
%X This paper describes our submission to the WMT2021 shared metrics task. Our metric is operative to segment-level and system-level translations. Our belief toward a better metric is to detect a significant error that cannot be missed in the real practice cases of evaluation. For that reason, we used pseudo-negative examples in which attributes of some words are transferred to the reversed attribute words, and we build evaluation models to handle such serious mistakes of translations. We fine-tune a multilingual largely pre-trained model on the provided corpus of past years’ metric task and fine-tune again further on the synthetic negative examples that are derived from the same fine-tune corpus. From the evaluation results of the WMT21‘s development corpus, fine-tuning on the pseudo-negatives using WMT15-17 and WMT18-20 metric corpus achieved a better Pearson‘s correlation score than the one fine-tuned without negative examples. Our submitted models,hyp+src_hyp+ref and hyp+src_hyp+ref.negative, are the plain model using WMT18-20 and the one additionally fine-tuned on negative samples, respectively.
%U https://aclanthology.org/2021.wmt-1.113/
%P 1049-1052
Markdown (Informal)
[Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for WMT 2021 Metrics Task](https://aclanthology.org/2021.wmt-1.113/) (Takahashi et al., WMT 2021)
ACL