<?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>
        <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
%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)

• Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for WMT 2021 Metrics Task (Takahashi et al., WMT 2021)

ACL

• Kosuke Takahashi, Yoichi Ishibashi, Katsuhito Sudoh, and Satoshi Nakamura. 2021. Multilingual Machine Translation Evaluation Metrics Fine-tuned on Pseudo-Negative Examples for WMT 2021 Metrics Task. In Proceedings of the Sixth Conference on Machine Translation, pages 1049–1052, Online. Association for Computational Linguistics.