IndT5: A Text-to-Text Transformer for 10 Indigenous Languages

El Moatez Billah Nagoudi, Wei-Rui Chen, Muhammad Abdul-Mageed, Hasan Cavusoglu


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.
Anthology ID:
2021.americasnlp-1.30
Volume:
Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
Month:
June
Year:
2021
Address:
Online
Editors:
Manuel Mager, Arturo Oncevay, Annette Rios, Ivan Vladimir Meza Ruiz, Alexis Palmer, Graham Neubig, Katharina Kann
Venue:
AmericasNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
265–271
Language:
URL:
https://aclanthology.org/2021.americasnlp-1.30
DOI:
10.18653/v1/2021.americasnlp-1.30
Bibkey:
Cite (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.
Cite (Informal):
IndT5: A Text-to-Text Transformer for 10 Indigenous Languages (Nagoudi et al., AmericasNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.americasnlp-1.30.pdf