@inproceedings{dhar-etal-2020-linguistically,
title = "Linguistically Motivated Subwords for {E}nglish-{T}amil Translation: {U}niversity of {G}roningen{'}s Submission to {WMT}-2020",
author = "Dhar, Prajit and
Bisazza, Arianna and
van Noord, Gertjan",
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-1.9",
pages = "126--133",
abstract = "This paper describes our submission for the English-Tamil news translation task of WMT-2020. The various techniques and Neural Machine Translation (NMT) models used by our team are presented and discussed, including back-translation, fine-tuning and word dropout. Additionally, our experiments show that using a linguistically motivated subword segmentation technique (Ataman et al., 2017) does not consistently outperform the more widely used, non-linguistically motivated SentencePiece algorithm (Kudo and Richardson, 2018), despite the agglutinative nature of Tamil morphology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhar-etal-2020-linguistically">
<titleInfo>
<title>Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prajit</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gertjan</namePart>
<namePart type="family">van Noord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</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 our submission for the English-Tamil news translation task of WMT-2020. The various techniques and Neural Machine Translation (NMT) models used by our team are presented and discussed, including back-translation, fine-tuning and word dropout. Additionally, our experiments show that using a linguistically motivated subword segmentation technique (Ataman et al., 2017) does not consistently outperform the more widely used, non-linguistically motivated SentencePiece algorithm (Kudo and Richardson, 2018), despite the agglutinative nature of Tamil morphology.</abstract>
<identifier type="citekey">dhar-etal-2020-linguistically</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.9</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>126</start>
<end>133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020
%A Dhar, Prajit
%A Bisazza, Arianna
%A van Noord, Gertjan
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F dhar-etal-2020-linguistically
%X This paper describes our submission for the English-Tamil news translation task of WMT-2020. The various techniques and Neural Machine Translation (NMT) models used by our team are presented and discussed, including back-translation, fine-tuning and word dropout. Additionally, our experiments show that using a linguistically motivated subword segmentation technique (Ataman et al., 2017) does not consistently outperform the more widely used, non-linguistically motivated SentencePiece algorithm (Kudo and Richardson, 2018), despite the agglutinative nature of Tamil morphology.
%U https://aclanthology.org/2020.wmt-1.9
%P 126-133
Markdown (Informal)
[Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020](https://aclanthology.org/2020.wmt-1.9) (Dhar et al., WMT 2020)
ACL