@inproceedings{nagoudi-etal-2021-indt5,
title = "{I}nd{T}5: A Text-to-Text Transformer for 10 Indigenous Languages",
author = "Nagoudi, El Moatez Billah and
Chen, Wei-Rui and
Abdul-Mageed, Muhammad and
Cavusoglu, Hasan",
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-1.30",
doi = "10.18653/v1/2021.americasnlp-1.30",
pages = "265--271",
abstract = "Transformer language models have become fundamental components of NLP based pipelines. Although several Transformer have been introduced to serve many languages, there is a shortage of models pre-trained for low-resource and Indigenous languages in particular. In this work, we introduce IndT5, the first Transformer language model for Indigenous languages. To train IndT5, we build IndCorpus, a new corpus for 10 Indigenous languages and Spanish. We also present the application of IndT5 to machine translation by investigating different approaches to translate between Spanish and the Indigenous languages as part of our contribution to the AmericasNLP 2021 Shared Task on Open Machine Translation. IndT5 and IndCorpus are publicly available for research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagoudi-etal-2021-indt5">
<titleInfo>
<title>IndT5: A Text-to-Text Transformer for 10 Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">El</namePart>
<namePart type="given">Moatez</namePart>
<namePart type="given">Billah</namePart>
<namePart type="family">Nagoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Rui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Cavusoglu</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>Transformer language models have become fundamental components of NLP based pipelines. Although several Transformer have been introduced to serve many languages, there is a shortage of models pre-trained for low-resource and Indigenous languages in particular. In this work, we introduce IndT5, the first Transformer language model for Indigenous languages. To train IndT5, we build IndCorpus, a new corpus for 10 Indigenous languages and Spanish. We also present the application of IndT5 to machine translation by investigating different approaches to translate between Spanish and the Indigenous languages as part of our contribution to the AmericasNLP 2021 Shared Task on Open Machine Translation. IndT5 and IndCorpus are publicly available for research.</abstract>
<identifier type="citekey">nagoudi-etal-2021-indt5</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.30</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.30</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>265</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndT5: A Text-to-Text Transformer for 10 Indigenous Languages
%A Nagoudi, El Moatez Billah
%A Chen, Wei-Rui
%A Abdul-Mageed, Muhammad
%A Cavusoglu, Hasan
%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 nagoudi-etal-2021-indt5
%X Transformer language models have become fundamental components of NLP based pipelines. Although several Transformer have been introduced to serve many languages, there is a shortage of models pre-trained for low-resource and Indigenous languages in particular. In this work, we introduce IndT5, the first Transformer language model for Indigenous languages. To train IndT5, we build IndCorpus, a new corpus for 10 Indigenous languages and Spanish. We also present the application of IndT5 to machine translation by investigating different approaches to translate between Spanish and the Indigenous languages as part of our contribution to the AmericasNLP 2021 Shared Task on Open Machine Translation. IndT5 and IndCorpus are publicly available for research.
%R 10.18653/v1/2021.americasnlp-1.30
%U https://aclanthology.org/2021.americasnlp-1.30
%U https://doi.org/10.18653/v1/2021.americasnlp-1.30
%P 265-271
Markdown (Informal)
[IndT5: A Text-to-Text Transformer for 10 Indigenous Languages](https://aclanthology.org/2021.americasnlp-1.30) (Nagoudi et al., AmericasNLP 2021)
ACL
- El Moatez Billah Nagoudi, Wei-Rui Chen, Muhammad Abdul-Mageed, and Hasan Cavusoglu. 2021. IndT5: A Text-to-Text Transformer for 10 Indigenous Languages. In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, pages 265–271, Online. Association for Computational Linguistics.