<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krislauks-pinnis-2020-tilde">
    <titleInfo>
        <title>Tilde at WMT 2020: News Task Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rihards</namePart>
        <namePart type="family">Krišlauks</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mārcis</namePart>
        <namePart type="family">Pinnis</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>This paper describes Tilde’s submission to the WMT2020 shared task on news translation for both directions of the English-Polish language pair in both the constrained and the unconstrained tracks. We follow our submissions form the previous years and build our baseline systems to be morphologically motivated sub-word unit-based Transformer base models that we train using the Marian machine translation toolkit. Additionally, we experiment with different parallel and monolingual data selection schemes, as well as sampled back-translation. Our final models are ensembles of Transformer base and Transformer big models which feature right-to-left re-ranking.</abstract>
    <identifier type="citekey">krislauks-pinnis-2020-tilde</identifier>
    <location>
        <url>https://aclanthology.org/2020.wmt-1.15</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>175</start>
            <end>180</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tilde at WMT 2020: News Task Systems
%A Krišlauks, Rihards
%A Pinnis, Mārcis
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F krislauks-pinnis-2020-tilde
%X This paper describes Tilde’s submission to the WMT2020 shared task on news translation for both directions of the English-Polish language pair in both the constrained and the unconstrained tracks. We follow our submissions form the previous years and build our baseline systems to be morphologically motivated sub-word unit-based Transformer base models that we train using the Marian machine translation toolkit. Additionally, we experiment with different parallel and monolingual data selection schemes, as well as sampled back-translation. Our final models are ensembles of Transformer base and Transformer big models which feature right-to-left re-ranking.
%U https://aclanthology.org/2020.wmt-1.15
%P 175-180

Markdown (Informal)

[Tilde at WMT 2020: News Task Systems](https://aclanthology.org/2020.wmt-1.15) (Krišlauks & Pinnis, WMT 2020)

• Tilde at WMT 2020: News Task Systems (Krišlauks & Pinnis, WMT 2020)

ACL

• Rihards Krišlauks and Mārcis Pinnis. 2020. Tilde at WMT 2020: News Task Systems. In Proceedings of the Fifth Conference on Machine Translation, pages 175–180, Online. Association for Computational Linguistics.