@inproceedings{zenkel-etal-2021-automatic-bilingual,
title = "Automatic Bilingual Markup Transfer",
author = "Zenkel, Thomas and
Wuebker, Joern and
DeNero, John",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.299",
doi = "10.18653/v1/2021.findings-emnlp.299",
pages = "3524--3533",
abstract = "We describe the task of bilingual markup transfer, which involves placing markup tags from a source sentence into a fixed target translation. This task arises in practice when a human translator generates the target translation without markup, and then the system infers the placement of markup tags. This task contrasts from previous work in which markup transfer is performed jointly with machine translation. We propose two novel metrics and evaluate several approaches based on unsupervised word alignments as well as a supervised neural sequence-to-sequence model. Our best approach achieves an average accuracy of 94.7{\%} across six language pairs, indicating its potential usefulness for real-world localization tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zenkel-etal-2021-automatic-bilingual">
<titleInfo>
<title>Automatic Bilingual Markup Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Zenkel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joern</namePart>
<namePart type="family">Wuebker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">DeNero</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>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the task of bilingual markup transfer, which involves placing markup tags from a source sentence into a fixed target translation. This task arises in practice when a human translator generates the target translation without markup, and then the system infers the placement of markup tags. This task contrasts from previous work in which markup transfer is performed jointly with machine translation. We propose two novel metrics and evaluate several approaches based on unsupervised word alignments as well as a supervised neural sequence-to-sequence model. Our best approach achieves an average accuracy of 94.7% across six language pairs, indicating its potential usefulness for real-world localization tasks.</abstract>
<identifier type="citekey">zenkel-etal-2021-automatic-bilingual</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.299</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.299</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3524</start>
<end>3533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Bilingual Markup Transfer
%A Zenkel, Thomas
%A Wuebker, Joern
%A DeNero, John
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zenkel-etal-2021-automatic-bilingual
%X We describe the task of bilingual markup transfer, which involves placing markup tags from a source sentence into a fixed target translation. This task arises in practice when a human translator generates the target translation without markup, and then the system infers the placement of markup tags. This task contrasts from previous work in which markup transfer is performed jointly with machine translation. We propose two novel metrics and evaluate several approaches based on unsupervised word alignments as well as a supervised neural sequence-to-sequence model. Our best approach achieves an average accuracy of 94.7% across six language pairs, indicating its potential usefulness for real-world localization tasks.
%R 10.18653/v1/2021.findings-emnlp.299
%U https://aclanthology.org/2021.findings-emnlp.299
%U https://doi.org/10.18653/v1/2021.findings-emnlp.299
%P 3524-3533
Markdown (Informal)
[Automatic Bilingual Markup Transfer](https://aclanthology.org/2021.findings-emnlp.299) (Zenkel et al., Findings 2021)
ACL
- Thomas Zenkel, Joern Wuebker, and John DeNero. 2021. Automatic Bilingual Markup Transfer. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3524–3533, Punta Cana, Dominican Republic. Association for Computational Linguistics.