@inproceedings{muradoglu-etal-2025-beyond,
title = "Beyond a Means to an End: A Case Study in Building Phonotactic Corpora for {C}entral {A}ustralian Languages",
author = "Muradoglu, Saliha and
Gray, James and
Simpson, Jane Helen and
Proctor, Michael and
Harvey, Mark",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.7/",
pages = "32--37",
ISBN = "978-9908-53-121-2",
abstract = "Linguistic datasets are essential across fields: computational linguists use them for NLP development, theoretical linguists for statistical arguments supporting hypotheses about language, and documentary linguists for preserving examples and aiding grammatical descriptions. Transforming raw data (e.g., recordings or dictionaries) into structured forms (e.g., tables) requires non-trivial decisions within processing pipelines.This paper highlights the importance of these processes in understanding linguistic systems. Our contributions include: (1) an interactive dashboard for four central Australian languages with custom filters, and (2) demonstrating how data processing decisions influence measured outcomes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muradoglu-etal-2025-beyond">
<titleInfo>
<title>Beyond a Means to an End: A Case Study in Building Phonotactic Corpora for Central Australian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Gray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jane</namePart>
<namePart type="given">Helen</namePart>
<namePart type="family">Simpson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Proctor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Harvey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>Linguistic datasets are essential across fields: computational linguists use them for NLP development, theoretical linguists for statistical arguments supporting hypotheses about language, and documentary linguists for preserving examples and aiding grammatical descriptions. Transforming raw data (e.g., recordings or dictionaries) into structured forms (e.g., tables) requires non-trivial decisions within processing pipelines.This paper highlights the importance of these processes in understanding linguistic systems. Our contributions include: (1) an interactive dashboard for four central Australian languages with custom filters, and (2) demonstrating how data processing decisions influence measured outcomes.</abstract>
<identifier type="citekey">muradoglu-etal-2025-beyond</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.7/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>32</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond a Means to an End: A Case Study in Building Phonotactic Corpora for Central Australian Languages
%A Muradoglu, Saliha
%A Gray, James
%A Simpson, Jane Helen
%A Proctor, Michael
%A Harvey, Mark
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F muradoglu-etal-2025-beyond
%X Linguistic datasets are essential across fields: computational linguists use them for NLP development, theoretical linguists for statistical arguments supporting hypotheses about language, and documentary linguists for preserving examples and aiding grammatical descriptions. Transforming raw data (e.g., recordings or dictionaries) into structured forms (e.g., tables) requires non-trivial decisions within processing pipelines.This paper highlights the importance of these processes in understanding linguistic systems. Our contributions include: (1) an interactive dashboard for four central Australian languages with custom filters, and (2) demonstrating how data processing decisions influence measured outcomes.
%U https://aclanthology.org/2025.resourceful-1.7/
%P 32-37
Markdown (Informal)
[Beyond a Means to an End: A Case Study in Building Phonotactic Corpora for Central Australian Languages](https://aclanthology.org/2025.resourceful-1.7/) (Muradoglu et al., RESOURCEFUL 2025)
ACL