@inproceedings{winkie-etal-2026-developing,
title = "Developing A {H}awaiian Corpus Toolkit for Data-Driven Language Learning",
author = "Winkie, Joseph and
Miller, Michol and
Wu, Winston",
editor = "Agyapong, Godfred and
Moeller, Sarah and
Arppe, Antti and
Marashian, Ali and
Rosenblum, Daisy",
booktitle = "Proceedings of the Ninth Workshop on the Use of Computational Methods in the Study of Endangered Languages ({C}omput{EL}-9)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.computel-1.18/",
pages = "167--176",
ISBN = "979-8-89176-422-4",
abstract = "This paper presents the development of an online multimodal corpus toolkit designed for data-driven language learning in Hawaiian. The toolkit supports corpus linguistics analyses including concordance/KWIC (Key Word In Context) searches, frequency analysis, collocation analyses, and complex queries with n-grams and regex pattern matching. Specifically designed for educators, students, and parents within the Hawaiian community, this easy-to-use tool facilitates a data-driven language learning process by enabling users to explore authentic language data, identify patterns, and develop deeper understanding of Hawaiian language structures through computational methods. By integrating corpus-based approaches into language education, this toolkit contributes significantly to preserving and promoting Hawaiian language learning and supports the broader community{'}s efforts in language revitalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winkie-etal-2026-developing">
<titleInfo>
<title>Developing A Hawaiian Corpus Toolkit for Data-Driven Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Winkie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michol</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Workshop on the Use of Computational Methods in the Study of Endangered Languages (ComputEL-9)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Godfred</namePart>
<namePart type="family">Agyapong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Marashian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisy</namePart>
<namePart type="family">Rosenblum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-422-4</identifier>
</relatedItem>
<abstract>This paper presents the development of an online multimodal corpus toolkit designed for data-driven language learning in Hawaiian. The toolkit supports corpus linguistics analyses including concordance/KWIC (Key Word In Context) searches, frequency analysis, collocation analyses, and complex queries with n-grams and regex pattern matching. Specifically designed for educators, students, and parents within the Hawaiian community, this easy-to-use tool facilitates a data-driven language learning process by enabling users to explore authentic language data, identify patterns, and develop deeper understanding of Hawaiian language structures through computational methods. By integrating corpus-based approaches into language education, this toolkit contributes significantly to preserving and promoting Hawaiian language learning and supports the broader community’s efforts in language revitalization.</abstract>
<identifier type="citekey">winkie-etal-2026-developing</identifier>
<location>
<url>https://aclanthology.org/2026.computel-1.18/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>167</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing A Hawaiian Corpus Toolkit for Data-Driven Language Learning
%A Winkie, Joseph
%A Miller, Michol
%A Wu, Winston
%Y Agyapong, Godfred
%Y Moeller, Sarah
%Y Arppe, Antti
%Y Marashian, Ali
%Y Rosenblum, Daisy
%S Proceedings of the Ninth Workshop on the Use of Computational Methods in the Study of Endangered Languages (ComputEL-9)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-422-4
%F winkie-etal-2026-developing
%X This paper presents the development of an online multimodal corpus toolkit designed for data-driven language learning in Hawaiian. The toolkit supports corpus linguistics analyses including concordance/KWIC (Key Word In Context) searches, frequency analysis, collocation analyses, and complex queries with n-grams and regex pattern matching. Specifically designed for educators, students, and parents within the Hawaiian community, this easy-to-use tool facilitates a data-driven language learning process by enabling users to explore authentic language data, identify patterns, and develop deeper understanding of Hawaiian language structures through computational methods. By integrating corpus-based approaches into language education, this toolkit contributes significantly to preserving and promoting Hawaiian language learning and supports the broader community’s efforts in language revitalization.
%U https://aclanthology.org/2026.computel-1.18/
%P 167-176
Markdown (Informal)
[Developing A Hawaiian Corpus Toolkit for Data-Driven Language Learning](https://aclanthology.org/2026.computel-1.18/) (Winkie et al., ComputEL 2026)
ACL