<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrando-etal-2022-towards">
    <titleInfo>
        <title>Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Javier</namePart>
        <namePart type="family">Ferrando</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gerard</namePart>
        <namePart type="given">I</namePart>
        <namePart type="family">Gállego</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Belen</namePart>
        <namePart type="family">Alastruey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Escolano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marta</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Costa-jussà</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens’ attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens’ attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.</abstract>
    <identifier type="citekey">ferrando-etal-2022-towards</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.599</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.599</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>8756</start>
            <end>8769</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
%A Ferrando, Javier
%A Gállego, Gerard I.
%A Alastruey, Belen
%A Escolano, Carlos
%A Costa-jussà, Marta R.
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F ferrando-etal-2022-towards
%X In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens’ attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens’ attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.
%R 10.18653/v1/2022.emnlp-main.599
%U https://aclanthology.org/2022.emnlp-main.599
%U https://doi.org/10.18653/v1/2022.emnlp-main.599
%P 8756-8769

Markdown (Informal)

[Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://aclanthology.org/2022.emnlp-main.599) (Ferrando et al., EMNLP 2022)

• Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer (Ferrando et al., EMNLP 2022)

ACL

• Javier Ferrando, Gerard I. Gállego, Belen Alastruey, Carlos Escolano, and Marta R. Costa-jussà. 2022. Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8756–8769, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.