@inproceedings{dabre-2022-nicts,
title = "{NICT}{'}s Submission to the {WAT} 2022 Structured Document Translation Task",
author = "Dabre, Raj",
booktitle = "Proceedings of the 9th Workshop on Asian Translation",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.wat-1.6",
pages = "64--67",
abstract = "We present our submission to the structured document translation task organized by WAT 2022. In structured document translation, the key challenge is the handling of inline tags, which annotate text. Specifically, the text that is annotated by tags, should be translated in such a way that in the translation should contain the tags annotating the translation. This challenge is further compounded by the lack of training data containing sentence pairs with inline XML tag annotated content. However, to our surprise, we find that existing multilingual NMT systems are able to handle the translation of text annotated with XML tags without any explicit training on data containing said tags. Specifically, massively multilingual translation models like M2M-100 perform well despite not being explicitly trained to handle structured content. This direct translation approach is often either as good as if not better than the traditional approach of {``}remove tag, translate and re-inject tag{''} also known as the {``}detag-and-project{''} approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-2022-nicts">
<titleInfo>
<title>NICT’s Submission to the WAT 2022 Structured Document Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Asian Translation</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our submission to the structured document translation task organized by WAT 2022. In structured document translation, the key challenge is the handling of inline tags, which annotate text. Specifically, the text that is annotated by tags, should be translated in such a way that in the translation should contain the tags annotating the translation. This challenge is further compounded by the lack of training data containing sentence pairs with inline XML tag annotated content. However, to our surprise, we find that existing multilingual NMT systems are able to handle the translation of text annotated with XML tags without any explicit training on data containing said tags. Specifically, massively multilingual translation models like M2M-100 perform well despite not being explicitly trained to handle structured content. This direct translation approach is often either as good as if not better than the traditional approach of “remove tag, translate and re-inject tag” also known as the “detag-and-project” approach.</abstract>
<identifier type="citekey">dabre-2022-nicts</identifier>
<location>
<url>https://aclanthology.org/2022.wat-1.6</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>64</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NICT’s Submission to the WAT 2022 Structured Document Translation Task
%A Dabre, Raj
%S Proceedings of the 9th Workshop on Asian Translation
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F dabre-2022-nicts
%X We present our submission to the structured document translation task organized by WAT 2022. In structured document translation, the key challenge is the handling of inline tags, which annotate text. Specifically, the text that is annotated by tags, should be translated in such a way that in the translation should contain the tags annotating the translation. This challenge is further compounded by the lack of training data containing sentence pairs with inline XML tag annotated content. However, to our surprise, we find that existing multilingual NMT systems are able to handle the translation of text annotated with XML tags without any explicit training on data containing said tags. Specifically, massively multilingual translation models like M2M-100 perform well despite not being explicitly trained to handle structured content. This direct translation approach is often either as good as if not better than the traditional approach of “remove tag, translate and re-inject tag” also known as the “detag-and-project” approach.
%U https://aclanthology.org/2022.wat-1.6
%P 64-67
Markdown (Informal)
[NICT’s Submission to the WAT 2022 Structured Document Translation Task](https://aclanthology.org/2022.wat-1.6) (Dabre, WAT 2022)
ACL