@inproceedings{andrews-etal-2022-stopes,
title = "stopes - Modular Machine Translation Pipelines",
author = "Andrews, Pierre and
Wenzek, Guillaume and
Heffernan, Kevin and
{\c{C}}elebi, Onur and
Sun, Anna and
Kamran, Ammar and
Guo, Yingzhe and
Mourachko, Alexandre and
Schwenk, Holger and
Fan, Angela",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.26/",
doi = "10.18653/v1/2022.emnlp-demos.26",
pages = "258--265",
abstract = "Neural machine translation, as other natural language deep learning applications, is hungry for data. As research evolves, the data pipelines supporting that research evolve too, oftentimes re-implementing the same core components. Despite the potential of modular codebases, researchers have but little time to put code structure and reusability first. Unfortunately, this makes it very hard to publish clean, reproducible code to benefit a wider audience. In this paper, we motivate and describe stopes , a framework that addresses these issues while empowering scalability and versatility for research use cases. This library was a key enabler of the No Language Left Behind project, establishing new state of the art performance for a multilingual machine translation model covering 200 languages. stopes and the pipelines described are released under the MIT license at \url{https://github.com/facebookresearch/stopes}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andrews-etal-2022-stopes">
<titleInfo>
<title>stopes - Modular Machine Translation Pipelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Andrews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Wenzek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Heffernan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Çelebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ammar</namePart>
<namePart type="family">Kamran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingzhe</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Mourachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holger</namePart>
<namePart type="family">Schwenk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural machine translation, as other natural language deep learning applications, is hungry for data. As research evolves, the data pipelines supporting that research evolve too, oftentimes re-implementing the same core components. Despite the potential of modular codebases, researchers have but little time to put code structure and reusability first. Unfortunately, this makes it very hard to publish clean, reproducible code to benefit a wider audience. In this paper, we motivate and describe stopes , a framework that addresses these issues while empowering scalability and versatility for research use cases. This library was a key enabler of the No Language Left Behind project, establishing new state of the art performance for a multilingual machine translation model covering 200 languages. stopes and the pipelines described are released under the MIT license at https://github.com/facebookresearch/stopes.</abstract>
<identifier type="citekey">andrews-etal-2022-stopes</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.26</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.26/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>258</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T stopes - Modular Machine Translation Pipelines
%A Andrews, Pierre
%A Wenzek, Guillaume
%A Heffernan, Kevin
%A Çelebi, Onur
%A Sun, Anna
%A Kamran, Ammar
%A Guo, Yingzhe
%A Mourachko, Alexandre
%A Schwenk, Holger
%A Fan, Angela
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F andrews-etal-2022-stopes
%X Neural machine translation, as other natural language deep learning applications, is hungry for data. As research evolves, the data pipelines supporting that research evolve too, oftentimes re-implementing the same core components. Despite the potential of modular codebases, researchers have but little time to put code structure and reusability first. Unfortunately, this makes it very hard to publish clean, reproducible code to benefit a wider audience. In this paper, we motivate and describe stopes , a framework that addresses these issues while empowering scalability and versatility for research use cases. This library was a key enabler of the No Language Left Behind project, establishing new state of the art performance for a multilingual machine translation model covering 200 languages. stopes and the pipelines described are released under the MIT license at https://github.com/facebookresearch/stopes.
%R 10.18653/v1/2022.emnlp-demos.26
%U https://aclanthology.org/2022.emnlp-demos.26/
%U https://doi.org/10.18653/v1/2022.emnlp-demos.26
%P 258-265
Markdown (Informal)
[stopes - Modular Machine Translation Pipelines](https://aclanthology.org/2022.emnlp-demos.26/) (Andrews et al., EMNLP 2022)
ACL
- Pierre Andrews, Guillaume Wenzek, Kevin Heffernan, Onur Çelebi, Anna Sun, Ammar Kamran, Yingzhe Guo, Alexandre Mourachko, Holger Schwenk, and Angela Fan. 2022. stopes - Modular Machine Translation Pipelines. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 258–265, Abu Dhabi, UAE. Association for Computational Linguistics.