@inproceedings{vazquez-etal-2021-helsinki,
title = "The {H}elsinki submission to the {A}mericas{NLP} shared task",
author = {V{\'a}zquez, Ra{\'u}l and
Scherrer, Yves and
Virpioja, Sami and
Tiedemann, J{\"o}rg},
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.29",
doi = "10.18653/v1/2021.americasnlp-1.29",
pages = "255--264",
abstract = "The University of Helsinki participated in the AmericasNLP shared task for all ten language pairs. Our multilingual NMT models reached the first rank on all language pairs in track 1, and first rank on nine out of ten language pairs in track 2. We focused our efforts on three aspects: (1) the collection of additional data from various sources such as Bibles and political constitutions, (2) the cleaning and filtering of training data with the OpusFilter toolkit, and (3) different multilingual training techniques enabled by the latest version of the OpenNMT-py toolkit to make the most efficient use of the scarce data. This paper describes our efforts in detail.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vazquez-etal-2021-helsinki">
<titleInfo>
<title>The Helsinki submission to the AmericasNLP shared task</title>
</titleInfo>
<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">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</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>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</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>The University of Helsinki participated in the AmericasNLP shared task for all ten language pairs. Our multilingual NMT models reached the first rank on all language pairs in track 1, and first rank on nine out of ten language pairs in track 2. We focused our efforts on three aspects: (1) the collection of additional data from various sources such as Bibles and political constitutions, (2) the cleaning and filtering of training data with the OpusFilter toolkit, and (3) different multilingual training techniques enabled by the latest version of the OpenNMT-py toolkit to make the most efficient use of the scarce data. This paper describes our efforts in detail.</abstract>
<identifier type="citekey">vazquez-etal-2021-helsinki</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.29</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.29</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>255</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Helsinki submission to the AmericasNLP shared task
%A Vázquez, Raúl
%A Scherrer, Yves
%A Virpioja, Sami
%A Tiedemann, Jörg
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F vazquez-etal-2021-helsinki
%X The University of Helsinki participated in the AmericasNLP shared task for all ten language pairs. Our multilingual NMT models reached the first rank on all language pairs in track 1, and first rank on nine out of ten language pairs in track 2. We focused our efforts on three aspects: (1) the collection of additional data from various sources such as Bibles and political constitutions, (2) the cleaning and filtering of training data with the OpusFilter toolkit, and (3) different multilingual training techniques enabled by the latest version of the OpenNMT-py toolkit to make the most efficient use of the scarce data. This paper describes our efforts in detail.
%R 10.18653/v1/2021.americasnlp-1.29
%U https://aclanthology.org/2021.americasnlp-1.29
%U https://doi.org/10.18653/v1/2021.americasnlp-1.29
%P 255-264
Markdown (Informal)
[The Helsinki submission to the AmericasNLP shared task](https://aclanthology.org/2021.americasnlp-1.29) (Vázquez et al., AmericasNLP 2021)
ACL
- Raúl Vázquez, Yves Scherrer, Sami Virpioja, and Jörg Tiedemann. 2021. The Helsinki submission to the AmericasNLP shared task. In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, pages 255–264, Online. Association for Computational Linguistics.