<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kharitonova-etal-2021-transfer">
    <titleInfo>
        <title>Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ksenia</namePart>
        <namePart type="family">Kharitonova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ona</namePart>
        <namePart type="family">de Gibert Bonet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordi</namePart>
        <namePart type="family">Armengol-Estapé</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mar</namePart>
        <namePart type="family">Rodriguez i Alvarez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maite</namePart>
        <namePart type="family">Melero</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 the participation of the BSC team in the WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task. The system aims to solve the Subtask 2: Wikipedia cultural heritage articles, which involves translation in four Romance languages: Catalan, Italian, Occitan and Romanian. The submitted system is a multilingual semi-supervised machine translation model. It is based on a pre-trained language model, namely XLM-RoBERTa, that is later fine-tuned with parallel data obtained mostly from OPUS. Unlike other works, we only use XLM to initialize the encoder and randomly initialize a shallow decoder. The reported results are robust and perform well for all tested languages.</abstract>
    <identifier type="citekey">kharitonova-etal-2021-transfer</identifier>
    <location>
        <url>https://aclanthology.org/2021.wmt-1.43</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>362</start>
            <end>367</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task
%A Kharitonova, Ksenia
%A de Gibert Bonet, Ona
%A Armengol-Estapé, Jordi
%A Rodriguez i Alvarez, Mar
%A Melero, Maite
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F kharitonova-etal-2021-transfer
%X This paper describes the participation of the BSC team in the WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task. The system aims to solve the Subtask 2: Wikipedia cultural heritage articles, which involves translation in four Romance languages: Catalan, Italian, Occitan and Romanian. The submitted system is a multilingual semi-supervised machine translation model. It is based on a pre-trained language model, namely XLM-RoBERTa, that is later fine-tuned with parallel data obtained mostly from OPUS. Unlike other works, we only use XLM to initialize the encoder and randomly initialize a shallow decoder. The reported results are robust and perform well for all tested languages.
%U https://aclanthology.org/2021.wmt-1.43
%P 362-367

Markdown (Informal)

[Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task](https://aclanthology.org/2021.wmt-1.43) (Kharitonova et al., WMT 2021)

• Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task (Kharitonova et al., WMT 2021)

ACL

• Ksenia Kharitonova, Ona de Gibert Bonet, Jordi Armengol-Estapé, Mar Rodriguez i Alvarez, and Maite Melero. 2021. Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task. In Proceedings of the Sixth Conference on Machine Translation, pages 362–367, Online. Association for Computational Linguistics.