@inproceedings{dobrowolski-etal-2021-samsung,
title = "{S}amsung {R}{\&}{D} Institute {P}oland submission to {WAT} 2021 Indic Language Multilingual Task",
author = "Dobrowolski, Adam and
Szyma{\'n}ski, Marcin and
Chochowski, Marcin and
Przybysz, Pawe{\l}",
booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wat-1.27",
doi = "10.18653/v1/2021.wat-1.27",
pages = "224--232",
abstract = "This paper describes the submission to the WAT 2021 Indic Language Multilingual Task by Samsung R{\&}D Institute Poland. The task covered translation between 10 Indic Languages (Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil and Telugu) and English. We combined a variety of techniques: transliteration, filtering, backtranslation, domain adaptation, knowledge-distillation and finally ensembling of NMT models. We applied an effective approach to low-resource training that consist of pretraining on backtranslations and tuning on parallel corpora. We experimented with two different domain-adaptation techniques which significantly improved translation quality when applied to monolingual corpora. We researched and applied a novel approach for finding the best hyperparameters for ensembling a number of translation models. All techniques combined gave significant improvement - up to +8 BLEU over baseline results. The quality of the models has been confirmed by the human evaluation where SRPOL models scored best for all 5 manually evaluated languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobrowolski-etal-2021-samsung">
<titleInfo>
<title>Samsung R&D Institute Poland submission to WAT 2021 Indic Language Multilingual Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Dobrowolski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Szymański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Chochowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Przybysz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Asian Translation (WAT2021)</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 the submission to the WAT 2021 Indic Language Multilingual Task by Samsung R&D Institute Poland. The task covered translation between 10 Indic Languages (Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil and Telugu) and English. We combined a variety of techniques: transliteration, filtering, backtranslation, domain adaptation, knowledge-distillation and finally ensembling of NMT models. We applied an effective approach to low-resource training that consist of pretraining on backtranslations and tuning on parallel corpora. We experimented with two different domain-adaptation techniques which significantly improved translation quality when applied to monolingual corpora. We researched and applied a novel approach for finding the best hyperparameters for ensembling a number of translation models. All techniques combined gave significant improvement - up to +8 BLEU over baseline results. The quality of the models has been confirmed by the human evaluation where SRPOL models scored best for all 5 manually evaluated languages.</abstract>
<identifier type="citekey">dobrowolski-etal-2021-samsung</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.27</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.27</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>224</start>
<end>232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Samsung R&D Institute Poland submission to WAT 2021 Indic Language Multilingual Task
%A Dobrowolski, Adam
%A Szymański, Marcin
%A Chochowski, Marcin
%A Przybysz, Paweł
%S Proceedings of the 8th Workshop on Asian Translation (WAT2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F dobrowolski-etal-2021-samsung
%X This paper describes the submission to the WAT 2021 Indic Language Multilingual Task by Samsung R&D Institute Poland. The task covered translation between 10 Indic Languages (Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil and Telugu) and English. We combined a variety of techniques: transliteration, filtering, backtranslation, domain adaptation, knowledge-distillation and finally ensembling of NMT models. We applied an effective approach to low-resource training that consist of pretraining on backtranslations and tuning on parallel corpora. We experimented with two different domain-adaptation techniques which significantly improved translation quality when applied to monolingual corpora. We researched and applied a novel approach for finding the best hyperparameters for ensembling a number of translation models. All techniques combined gave significant improvement - up to +8 BLEU over baseline results. The quality of the models has been confirmed by the human evaluation where SRPOL models scored best for all 5 manually evaluated languages.
%R 10.18653/v1/2021.wat-1.27
%U https://aclanthology.org/2021.wat-1.27
%U https://doi.org/10.18653/v1/2021.wat-1.27
%P 224-232
Markdown (Informal)
[Samsung R&D Institute Poland submission to WAT 2021 Indic Language Multilingual Task](https://aclanthology.org/2021.wat-1.27) (Dobrowolski et al., WAT 2021)
ACL