<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="n-elnokrashy-etal-2022-language">
    <titleInfo>
        <title>Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">ElNokrashy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amr</namePart>
        <namePart type="family">Hendy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Maher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Afify</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hany</namePart>
        <namePart type="family">Hassan Awadalla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francisco</namePart>
            <namePart type="family">Guzmán</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Orlando, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper proposes a simple yet effective method to improve direct (X-to-Y) translation for both cases: zero-shot and when direct data is available. We modify the input tokens at both the encoder and decoder to include signals for the source and target languages. We show a performance gain when training from scratch, or finetuning a pretrained model with the pro- posed setup. In the experiments, our method shows nearly 10.0 BLEU points gain on in-house datasets depending on the checkpoint selection criteria. In a WMT evaluation campaign, From- English performance improves by 4.17 and 2.87 BLEU points, in the zero-shot setting, and when direct data is available for training, respectively. While X-to-Y improves by 1.29 BLEU over the zero-shot baseline, and 0.44 over the many-to-many baseline. In the low-resource setting, we see a 1.5 \ensuremath\sim 1.7 point improvement when finetuning on X-to-Y domain data.</abstract>
    <identifier type="citekey">n-elnokrashy-etal-2022-language</identifier>
    <location>
        <url>https://aclanthology.org/2022.amta-research.6/</url>
    </location>
    <part>
        <date>2022-09</date>
        <extent unit="page">
            <start>70</start>
            <end>82</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
%A ElNokrashy, Muhammad
%A Hendy, Amr
%A Maher, Mohamed
%A Afify, Mohamed
%A Hassan Awadalla, Hany
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F n-elnokrashy-etal-2022-language
%X This paper proposes a simple yet effective method to improve direct (X-to-Y) translation for both cases: zero-shot and when direct data is available. We modify the input tokens at both the encoder and decoder to include signals for the source and target languages. We show a performance gain when training from scratch, or finetuning a pretrained model with the pro- posed setup. In the experiments, our method shows nearly 10.0 BLEU points gain on in-house datasets depending on the checkpoint selection criteria. In a WMT evaluation campaign, From- English performance improves by 4.17 and 2.87 BLEU points, in the zero-shot setting, and when direct data is available for training, respectively. While X-to-Y improves by 1.29 BLEU over the zero-shot baseline, and 0.44 over the many-to-many baseline. In the low-resource setting, we see a 1.5 \ensuremath\sim 1.7 point improvement when finetuning on X-to-Y domain data.
%U https://aclanthology.org/2022.amta-research.6/
%P 70-82

Markdown (Informal)

[Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation](https://aclanthology.org/2022.amta-research.6/) (ElNokrashy et al., AMTA 2022)

• Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation (ElNokrashy et al., AMTA 2022)

ACL

• Muhammad ElNokrashy, Amr Hendy, Mohamed Maher, Mohamed Afify, and Hany Hassan Awadalla. 2022. Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 70–82, Orlando, USA. Association for Machine Translation in the Americas.