<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stahlberg-etal-2018-operation">
    <titleInfo>
        <title>An Operation Sequence Model for Explainable Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Felix</namePart>
        <namePart type="family">Stahlberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danielle</namePart>
        <namePart type="family">Saunders</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bill</namePart>
        <namePart type="family">Byrne</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tal</namePart>
            <namePart type="family">Linzen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Grzegorz</namePart>
            <namePart type="family">Chrupała</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Afra</namePart>
            <namePart type="family">Alishahi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the target sentence by monotonically walking through the source sentence. Word reordering is modeled by operations which allow setting markers in the target sentence and move a target-side write head between those markers. In contrast to many modern neural models, our system emits explicit word alignment information which is often crucial to practical machine translation as it improves explainability. Our technique can outperform a plain text system in terms of BLEU score under the recent Transformer architecture on Japanese-English and Portuguese-English, and is within 0.5 BLEU difference on Spanish-English.</abstract>
    <identifier type="citekey">stahlberg-etal-2018-operation</identifier>
    <identifier type="doi">10.18653/v1/W18-5420</identifier>
    <location>
        <url>https://aclanthology.org/W18-5420</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>175</start>
            <end>186</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T An Operation Sequence Model for Explainable Neural Machine Translation
%A Stahlberg, Felix
%A Saunders, Danielle
%A Byrne, Bill
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F stahlberg-etal-2018-operation
%X We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the target sentence by monotonically walking through the source sentence. Word reordering is modeled by operations which allow setting markers in the target sentence and move a target-side write head between those markers. In contrast to many modern neural models, our system emits explicit word alignment information which is often crucial to practical machine translation as it improves explainability. Our technique can outperform a plain text system in terms of BLEU score under the recent Transformer architecture on Japanese-English and Portuguese-English, and is within 0.5 BLEU difference on Spanish-English.
%R 10.18653/v1/W18-5420
%U https://aclanthology.org/W18-5420
%U https://doi.org/10.18653/v1/W18-5420
%P 175-186

Markdown (Informal)

[An Operation Sequence Model for Explainable Neural Machine Translation](https://aclanthology.org/W18-5420) (Stahlberg et al., EMNLP 2018)

• An Operation Sequence Model for Explainable Neural Machine Translation (Stahlberg et al., EMNLP 2018)

ACL

• Felix Stahlberg, Danielle Saunders, and Bill Byrne. 2018. An Operation Sequence Model for Explainable Neural Machine Translation. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 175–186, Brussels, Belgium. Association for Computational Linguistics.