@inproceedings{spencer-2024-documenting,
title = "Documenting Endangered Languages with {L}ang{D}oc: A Wordlist-Based System and A Case Study on {M}oklen",
author = "Spencer, Piyapath",
editor = "Serikov, Oleg and
Voloshina, Ekaterina and
Postnikova, Anna and
Muradoglu, Saliha and
Le Ferrand, Eric and
Klyachko, Elena and
Vylomova, Ekaterina and
Shavrina, Tatiana and
Tyers, Francis",
booktitle = "Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.fieldmatters-1.4/",
doi = "10.18653/v1/2024.fieldmatters-1.4",
pages = "28--36",
abstract = "Language documentation, especially languages lacking standardised writing systems, is a laborious and time-consuming process. This paper introduces LangDoc, a comprehensive system designed to address challenges and improve the efficiency and accuracy of language documentation projects. LangDoc offers several features, including tools for managing, recording, and reviewing the collected data. It operates both online and offline, crucial for fieldwork in remote locations. The paper also presents a comparative analysis demonstrating LangDoc`s efficiency compared to other methods. A case study of the Moklen language documentation project demonstrates how the features address the specific challenges of working with endangered languages and remote communities. Future development areas include integrating with NLP tools for advanced linguistic analysis and emphasising its potential to support the preservation of language diversity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spencer-2024-documenting">
<titleInfo>
<title>Documenting Endangered Languages with LangDoc: A Wordlist-Based System and A Case Study on Moklen</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piyapath</namePart>
<namePart type="family">Spencer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Voloshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Postnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Le Ferrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Klyachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language documentation, especially languages lacking standardised writing systems, is a laborious and time-consuming process. This paper introduces LangDoc, a comprehensive system designed to address challenges and improve the efficiency and accuracy of language documentation projects. LangDoc offers several features, including tools for managing, recording, and reviewing the collected data. It operates both online and offline, crucial for fieldwork in remote locations. The paper also presents a comparative analysis demonstrating LangDoc‘s efficiency compared to other methods. A case study of the Moklen language documentation project demonstrates how the features address the specific challenges of working with endangered languages and remote communities. Future development areas include integrating with NLP tools for advanced linguistic analysis and emphasising its potential to support the preservation of language diversity.</abstract>
<identifier type="citekey">spencer-2024-documenting</identifier>
<identifier type="doi">10.18653/v1/2024.fieldmatters-1.4</identifier>
<location>
<url>https://aclanthology.org/2024.fieldmatters-1.4/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>28</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Documenting Endangered Languages with LangDoc: A Wordlist-Based System and A Case Study on Moklen
%A Spencer, Piyapath
%Y Serikov, Oleg
%Y Voloshina, Ekaterina
%Y Postnikova, Anna
%Y Muradoglu, Saliha
%Y Le Ferrand, Eric
%Y Klyachko, Elena
%Y Vylomova, Ekaterina
%Y Shavrina, Tatiana
%Y Tyers, Francis
%S Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F spencer-2024-documenting
%X Language documentation, especially languages lacking standardised writing systems, is a laborious and time-consuming process. This paper introduces LangDoc, a comprehensive system designed to address challenges and improve the efficiency and accuracy of language documentation projects. LangDoc offers several features, including tools for managing, recording, and reviewing the collected data. It operates both online and offline, crucial for fieldwork in remote locations. The paper also presents a comparative analysis demonstrating LangDoc‘s efficiency compared to other methods. A case study of the Moklen language documentation project demonstrates how the features address the specific challenges of working with endangered languages and remote communities. Future development areas include integrating with NLP tools for advanced linguistic analysis and emphasising its potential to support the preservation of language diversity.
%R 10.18653/v1/2024.fieldmatters-1.4
%U https://aclanthology.org/2024.fieldmatters-1.4/
%U https://doi.org/10.18653/v1/2024.fieldmatters-1.4
%P 28-36
Markdown (Informal)
[Documenting Endangered Languages with LangDoc: A Wordlist-Based System and A Case Study on Moklen](https://aclanthology.org/2024.fieldmatters-1.4/) (Spencer, FieldMatters 2024)
ACL