@inproceedings{hanneman-dinu-2020-markup,
title = "How Should Markup Tags Be Translated?",
author = "Hanneman, Greg and
Dinu, Georgiana",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.138",
pages = "1160--1173",
abstract = "The ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup tags and tests the ability of MT models to learn tag placement via training data augmentation. We study the interactions of tag representation, data augmentation size, tag complexity, and language pair to show the drawbacks and benefits of each method. We construct and release new test sets containing tagged data for three language pairs of varying difficulty.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanneman-dinu-2020-markup">
<titleInfo>
<title>How Should Markup Tags Be Translated?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Hanneman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgiana</namePart>
<namePart type="family">Dinu</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>The ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup tags and tests the ability of MT models to learn tag placement via training data augmentation. We study the interactions of tag representation, data augmentation size, tag complexity, and language pair to show the drawbacks and benefits of each method. We construct and release new test sets containing tagged data for three language pairs of varying difficulty.</abstract>
<identifier type="citekey">hanneman-dinu-2020-markup</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.138</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1160</start>
<end>1173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Should Markup Tags Be Translated?
%A Hanneman, Greg
%A Dinu, Georgiana
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hanneman-dinu-2020-markup
%X The ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup tags and tests the ability of MT models to learn tag placement via training data augmentation. We study the interactions of tag representation, data augmentation size, tag complexity, and language pair to show the drawbacks and benefits of each method. We construct and release new test sets containing tagged data for three language pairs of varying difficulty.
%U https://aclanthology.org/2020.wmt-1.138
%P 1160-1173
Markdown (Informal)
[How Should Markup Tags Be Translated?](https://aclanthology.org/2020.wmt-1.138) (Hanneman & Dinu, WMT 2020)
ACL
- Greg Hanneman and Georgiana Dinu. 2020. How Should Markup Tags Be Translated?. In Proceedings of the Fifth Conference on Machine Translation, pages 1160–1173, Online. Association for Computational Linguistics.