@inproceedings{mickus-etal-2024-mammoth,
title = "{MAMMOTH}: Massively Multilingual Modular Open Translation @ {H}elsinki",
author = {Mickus, Timothee and
Gr{\"o}nroos, Stig-Arne and
Attieh, Joseph and
Boggia, Michele and
De Gibert, Ona and
Ji, Shaoxiong and
Loppi, Niki Andreas and
Raganato, Alessandro and
V{\'a}zquez, Ra{\'u}l and
Tiedemann, J{\"o}rg},
editor = "Aletras, Nikolaos and
De Clercq, Orphee",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-demo.14",
pages = "127--136",
abstract = "NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary step into the direction of designing smaller sub-networks and components with specialized functionality. In this paper, we present the MAMMOTH toolkit: a framework designed for training massively multilingual modular machine translation systems at scale, initially derived from OpenNMT-py and then adapted to ensure efficient training across computation clusters.We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information.The toolkit is publicly available online at https://github.com/Helsinki-NLP/mammoth.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mickus-etal-2024-mammoth">
<titleInfo>
<title>MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timothee</namePart>
<namePart type="family">Mickus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stig-Arne</namePart>
<namePart type="family">Grönroos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Attieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Boggia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">De Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoxiong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niki</namePart>
<namePart type="given">Andreas</namePart>
<namePart type="family">Loppi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary step into the direction of designing smaller sub-networks and components with specialized functionality. In this paper, we present the MAMMOTH toolkit: a framework designed for training massively multilingual modular machine translation systems at scale, initially derived from OpenNMT-py and then adapted to ensure efficient training across computation clusters.We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information.The toolkit is publicly available online at https://github.com/Helsinki-NLP/mammoth.</abstract>
<identifier type="citekey">mickus-etal-2024-mammoth</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-demo.14</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>127</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki
%A Mickus, Timothee
%A Grönroos, Stig-Arne
%A Attieh, Joseph
%A Boggia, Michele
%A De Gibert, Ona
%A Ji, Shaoxiong
%A Loppi, Niki Andreas
%A Raganato, Alessandro
%A Vázquez, Raúl
%A Tiedemann, Jörg
%Y Aletras, Nikolaos
%Y De Clercq, Orphee
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F mickus-etal-2024-mammoth
%X NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary step into the direction of designing smaller sub-networks and components with specialized functionality. In this paper, we present the MAMMOTH toolkit: a framework designed for training massively multilingual modular machine translation systems at scale, initially derived from OpenNMT-py and then adapted to ensure efficient training across computation clusters.We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information.The toolkit is publicly available online at https://github.com/Helsinki-NLP/mammoth.
%U https://aclanthology.org/2024.eacl-demo.14
%P 127-136
Markdown (Informal)
[MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki](https://aclanthology.org/2024.eacl-demo.14) (Mickus et al., EACL 2024)
ACL
- Timothee Mickus, Stig-Arne Grönroos, Joseph Attieh, Michele Boggia, Ona De Gibert, Shaoxiong Ji, Niki Andreas Loppi, Alessandro Raganato, Raúl Vázquez, and Jörg Tiedemann. 2024. MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 127–136, St. Julians, Malta. Association for Computational Linguistics.