@inproceedings{pugh-tyers-2021-investigating,
title = "Investigating variation in written forms of {N}ahuatl using character-based language models",
author = "Pugh, Robert and
Tyers, Francis",
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-1.3/",
doi = "10.18653/v1/2021.americasnlp-1.3",
pages = "21--27",
abstract = "We describe experiments with character-based language modeling for written variants of Nahuatl. Using a standard LSTM model and publicly available Bible translations, we explore how character language models can be applied to the tasks of estimating mutual intelligibility, identifying genetic similarity, and distinguishing written variants. We demonstrate that these simple language models are able to capture similarities and differences that have been described in the linguistic literature."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pugh-tyers-2021-investigating">
<titleInfo>
<title>Investigating variation in written forms of Nahuatl using character-based language models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</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>We describe experiments with character-based language modeling for written variants of Nahuatl. Using a standard LSTM model and publicly available Bible translations, we explore how character language models can be applied to the tasks of estimating mutual intelligibility, identifying genetic similarity, and distinguishing written variants. We demonstrate that these simple language models are able to capture similarities and differences that have been described in the linguistic literature.</abstract>
<identifier type="citekey">pugh-tyers-2021-investigating</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.3/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>21</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating variation in written forms of Nahuatl using character-based language models
%A Pugh, Robert
%A Tyers, Francis
%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 pugh-tyers-2021-investigating
%X We describe experiments with character-based language modeling for written variants of Nahuatl. Using a standard LSTM model and publicly available Bible translations, we explore how character language models can be applied to the tasks of estimating mutual intelligibility, identifying genetic similarity, and distinguishing written variants. We demonstrate that these simple language models are able to capture similarities and differences that have been described in the linguistic literature.
%R 10.18653/v1/2021.americasnlp-1.3
%U https://aclanthology.org/2021.americasnlp-1.3/
%U https://doi.org/10.18653/v1/2021.americasnlp-1.3
%P 21-27
Markdown (Informal)
[Investigating variation in written forms of Nahuatl using character-based language models](https://aclanthology.org/2021.americasnlp-1.3/) (Pugh & Tyers, AmericasNLP 2021)
ACL