<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-2020-cross">
    <titleInfo>
        <title>Cross-Lingual Transformers for Neural Automatic Post-Editing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dongjun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifth 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>In this paper, we describe the Bering Lab’s submission to the WMT 2020 Shared Task on Automatic Post-Editing (APE). First, we propose a cross-lingual Transformer architecture that takes a concatenation of a source sentence and a machine-translated (MT) sentence as an input to generate the post-edited (PE) output. For further improvement, we mask incorrect or missing words in the PE output based on word-level quality estimation and then predict the actual word for each mask based on the fine-tuned cross-lingual language model (XLM-RoBERTa). Finally, to address the over-correction problem, we select the final output among the PE outputs and the original MT sentence based on a sentence-level quality estimation. When evaluated on the WMT 2020 English-German APE test dataset, our system improves the NMT output by -3.95 and +4.50 in terms of TER and BLEU, respectively.</abstract>
    <identifier type="citekey">lee-2020-cross</identifier>
    <location>
        <url>https://aclanthology.org/2020.wmt-1.81</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>772</start>
            <end>776</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Lingual Transformers for Neural Automatic Post-Editing
%A Lee, Dongjun
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lee-2020-cross
%X In this paper, we describe the Bering Lab’s submission to the WMT 2020 Shared Task on Automatic Post-Editing (APE). First, we propose a cross-lingual Transformer architecture that takes a concatenation of a source sentence and a machine-translated (MT) sentence as an input to generate the post-edited (PE) output. For further improvement, we mask incorrect or missing words in the PE output based on word-level quality estimation and then predict the actual word for each mask based on the fine-tuned cross-lingual language model (XLM-RoBERTa). Finally, to address the over-correction problem, we select the final output among the PE outputs and the original MT sentence based on a sentence-level quality estimation. When evaluated on the WMT 2020 English-German APE test dataset, our system improves the NMT output by -3.95 and +4.50 in terms of TER and BLEU, respectively.
%U https://aclanthology.org/2020.wmt-1.81
%P 772-776

Markdown (Informal)

[Cross-Lingual Transformers for Neural Automatic Post-Editing](https://aclanthology.org/2020.wmt-1.81) (Lee, WMT 2020)

• Cross-Lingual Transformers for Neural Automatic Post-Editing (Lee, WMT 2020)

ACL

• Dongjun Lee. 2020. Cross-Lingual Transformers for Neural Automatic Post-Editing. In Proceedings of the Fifth Conference on Machine Translation, pages 772–776, Online. Association for Computational Linguistics.