@inproceedings{budiwati-etal-2021-optimize,
title = "To Optimize, or Not to Optimize, That Is the Question: {T}el{U}-{KU} Models for {WMT}21 Large-Scale Multilingual Machine Translation",
author = "Budiwati, Sari Dewi and
Fatyanosa, Tirana and
Data, Mahendra and
Wijaya, Dedy Rahman and
Telnoni, Patrick Adolf and
Suryani, Arie Ardiyanti and
Pratondo, Agus and
Aritsugi, Masayoshi",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.47",
pages = "387--397",
abstract = "We describe TelU-KU models of large-scale multilingual machine translation for five Southeast Asian languages: Javanese, Indonesian, Malay, Tagalog, Tamil, and English. We explore a variation of hyperparameters of flores101{\_}mm100{\_}175M model using random search with 10{\%} of datasets to improve BLEU scores of all thirty language pairs. We submitted two models, TelU-KU-175M and TelU-KU- 175M{\_}HPO, with average BLEU scores of 12.46 and 13.19, respectively. Our models show improvement in most language pairs after optimizing the hyperparameters. We also identified three language pairs that obtained a BLEU score of more than 15 while using less than 70 sentences of the training dataset: Indonesian-Tagalog, Tagalog-Indonesian, and Malay-Tagalog.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="budiwati-etal-2021-optimize">
<titleInfo>
<title>To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sari</namePart>
<namePart type="given">Dewi</namePart>
<namePart type="family">Budiwati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirana</namePart>
<namePart type="family">Fatyanosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahendra</namePart>
<namePart type="family">Data</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dedy</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Wijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="given">Adolf</namePart>
<namePart type="family">Telnoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arie</namePart>
<namePart type="given">Ardiyanti</namePart>
<namePart type="family">Suryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agus</namePart>
<namePart type="family">Pratondo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masayoshi</namePart>
<namePart type="family">Aritsugi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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>We describe TelU-KU models of large-scale multilingual machine translation for five Southeast Asian languages: Javanese, Indonesian, Malay, Tagalog, Tamil, and English. We explore a variation of hyperparameters of flores101_mm100_175M model using random search with 10% of datasets to improve BLEU scores of all thirty language pairs. We submitted two models, TelU-KU-175M and TelU-KU- 175M_HPO, with average BLEU scores of 12.46 and 13.19, respectively. Our models show improvement in most language pairs after optimizing the hyperparameters. We also identified three language pairs that obtained a BLEU score of more than 15 while using less than 70 sentences of the training dataset: Indonesian-Tagalog, Tagalog-Indonesian, and Malay-Tagalog.</abstract>
<identifier type="citekey">budiwati-etal-2021-optimize</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.47</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>387</start>
<end>397</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation
%A Budiwati, Sari Dewi
%A Fatyanosa, Tirana
%A Data, Mahendra
%A Wijaya, Dedy Rahman
%A Telnoni, Patrick Adolf
%A Suryani, Arie Ardiyanti
%A Pratondo, Agus
%A Aritsugi, Masayoshi
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F budiwati-etal-2021-optimize
%X We describe TelU-KU models of large-scale multilingual machine translation for five Southeast Asian languages: Javanese, Indonesian, Malay, Tagalog, Tamil, and English. We explore a variation of hyperparameters of flores101_mm100_175M model using random search with 10% of datasets to improve BLEU scores of all thirty language pairs. We submitted two models, TelU-KU-175M and TelU-KU- 175M_HPO, with average BLEU scores of 12.46 and 13.19, respectively. Our models show improvement in most language pairs after optimizing the hyperparameters. We also identified three language pairs that obtained a BLEU score of more than 15 while using less than 70 sentences of the training dataset: Indonesian-Tagalog, Tagalog-Indonesian, and Malay-Tagalog.
%U https://aclanthology.org/2021.wmt-1.47
%P 387-397
Markdown (Informal)
[To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation](https://aclanthology.org/2021.wmt-1.47) (Budiwati et al., WMT 2021)
ACL
- Sari Dewi Budiwati, Tirana Fatyanosa, Mahendra Data, Dedy Rahman Wijaya, Patrick Adolf Telnoni, Arie Ardiyanti Suryani, Agus Pratondo, and Masayoshi Aritsugi. 2021. To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation. In Proceedings of the Sixth Conference on Machine Translation, pages 387–397, Online. Association for Computational Linguistics.