How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task
Rahul Aralikatte, Héctor Ricardo Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, Anders Søgaard
Correct Metadata for
Abstract
This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for a maximum of 100 hours and get within 4-5 BLEU points of the top submission on the leaderboard. We also benchmark standard baselines on the PMI corpus and re-discover well-known shortcomings of translation systems and metrics.- Anthology ID:
- 2021.wat-1.24
- Volume:
- Proceedings of the 8th Workshop on Asian Translation (WAT2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Toshiaki Nakazawa, Hideki Nakayama, Isao Goto, Hideya Mino, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Shohei Higashiyama, Hiroshi Manabe, Win Pa Pa, Shantipriya Parida, Ondřej Bojar, Chenhui Chu, Akiko Eriguchi, Kaori Abe, Yusuke Oda, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 205–211
- Language:
- URL:
- https://aclanthology.org/2021.wat-1.24/
- DOI:
- 10.18653/v1/2021.wat-1.24
- Bibkey:
- Cite (ACL):
- Rahul Aralikatte, Héctor Ricardo Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, and Anders Søgaard. 2021. How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 205–211, Online. Association for Computational Linguistics.
- Cite (Informal):
- How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task (Aralikatte et al., WAT 2021)
- Copy Citation:
- PDF:
- https://aclanthology.org/2021.wat-1.24.pdf
Export citation
@inproceedings{aralikatte-etal-2021-far,
title = "How far can we get with one {GPU} in 100 hours? {C}o{AS}ta{L} at {M}ulti{I}ndic{MT} Shared Task",
author = "Aralikatte, Rahul and
Murrieta Bello, H{\'e}ctor Ricardo and
de Lhoneux, Miryam and
Hershcovich, Daniel and
Bollmann, Marcel and
S{\o}gaard, Anders",
editor = "Nakazawa, Toshiaki and
Nakayama, Hideki and
Goto, Isao and
Mino, Hideya and
Ding, Chenchen and
Dabre, Raj and
Kunchukuttan, Anoop and
Higashiyama, Shohei and
Manabe, Hiroshi and
Pa, Win Pa and
Parida, Shantipriya and
Bojar, Ond{\v{r}}ej and
Chu, Chenhui and
Eriguchi, Akiko and
Abe, Kaori and
Oda, Yusuke and
Sudoh, Katsuhito and
Kurohashi, Sadao and
Bhattacharyya, Pushpak",
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-1.24/",
doi = "10.18653/v1/2021.wat-1.24",
pages = "205--211",
abstract = "This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for a maximum of 100 hours and get within 4-5 BLEU points of the top submission on the leaderboard. We also benchmark standard baselines on the PMI corpus and re-discover well-known shortcomings of translation systems and metrics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aralikatte-etal-2021-far">
<titleInfo>
<title>How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Aralikatte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Héctor</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="family">Murrieta Bello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miryam</namePart>
<namePart type="family">de Lhoneux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Bollmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</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>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideya</namePart>
<namePart type="family">Mino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Manabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Win</namePart>
<namePart type="given">Pa</namePart>
<namePart type="family">Pa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Eriguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaori</namePart>
<namePart type="family">Abe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for a maximum of 100 hours and get within 4-5 BLEU points of the top submission on the leaderboard. We also benchmark standard baselines on the PMI corpus and re-discover well-known shortcomings of translation systems and metrics.</abstract>
<identifier type="citekey">aralikatte-etal-2021-far</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.24</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.24/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>205</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task %A Aralikatte, Rahul %A Murrieta Bello, Héctor Ricardo %A de Lhoneux, Miryam %A Hershcovich, Daniel %A Bollmann, Marcel %A Søgaard, Anders %Y Nakazawa, Toshiaki %Y Nakayama, Hideki %Y Goto, Isao %Y Mino, Hideya %Y Ding, Chenchen %Y Dabre, Raj %Y Kunchukuttan, Anoop %Y Higashiyama, Shohei %Y Manabe, Hiroshi %Y Pa, Win Pa %Y Parida, Shantipriya %Y Bojar, Ondřej %Y Chu, Chenhui %Y Eriguchi, Akiko %Y Abe, Kaori %Y Oda, Yusuke %Y Sudoh, Katsuhito %Y Kurohashi, Sadao %Y Bhattacharyya, Pushpak %S Proceedings of the 8th Workshop on Asian Translation (WAT2021) %D 2021 %8 August %I Association for Computational Linguistics %C Online %F aralikatte-etal-2021-far %X This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for a maximum of 100 hours and get within 4-5 BLEU points of the top submission on the leaderboard. We also benchmark standard baselines on the PMI corpus and re-discover well-known shortcomings of translation systems and metrics. %R 10.18653/v1/2021.wat-1.24 %U https://aclanthology.org/2021.wat-1.24/ %U https://doi.org/10.18653/v1/2021.wat-1.24 %P 205-211
Markdown (Informal)
[How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task](https://aclanthology.org/2021.wat-1.24/) (Aralikatte et al., WAT 2021)
- How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task (Aralikatte et al., WAT 2021)
ACL
- Rahul Aralikatte, Héctor Ricardo Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, and Anders Søgaard. 2021. How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 205–211, Online. Association for Computational Linguistics.