@inproceedings{riaposov-etal-2022-bringing,
title = "Bringing Together Version Control and Quality Assurance of Language Data with {LAMA}",
author = "Riaposov, Aleksandr and
Lazarenko, Elena and
Lehmberg, Timm",
editor = "Ojha, Atul Kr. and
Ahmadi, Sina and
Liu, Chao-Hong and
McCrae, John P.",
booktitle = "Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.eurali-1.6",
pages = "36--41",
abstract = "This contribution reports on work in process on project specific software and digital infrastructure components used along with corpus curation workflows in the the framework of the long-term language documentation project INEL. By bringing together scientists with different levels of technical affinity in a highly interdisciplinary working environment, the project is confronted with numerous workflow related issues. Many of them result from collaborative (remote-)work on digital corpora, which, among other things, include annotation, glossing but also quality- and consistency control. In this context several steps were taken to bridge the gap between usability and the requirements of complex data curation workflows. Components of the latter such as a versioning system and semi-automated data validators on one side meet the user demands for the simplicity and minimalism on the other side. Embodying a simple shell script in an interactive graphic user interface, we augment the efficacy of the data versioning and the integration of Java-based quality control and validation tools.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riaposov-etal-2022-bringing">
<titleInfo>
<title>Bringing Together Version Control and Quality Assurance of Language Data with LAMA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Riaposov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Lazarenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timm</namePart>
<namePart type="family">Lehmberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This contribution reports on work in process on project specific software and digital infrastructure components used along with corpus curation workflows in the the framework of the long-term language documentation project INEL. By bringing together scientists with different levels of technical affinity in a highly interdisciplinary working environment, the project is confronted with numerous workflow related issues. Many of them result from collaborative (remote-)work on digital corpora, which, among other things, include annotation, glossing but also quality- and consistency control. In this context several steps were taken to bridge the gap between usability and the requirements of complex data curation workflows. Components of the latter such as a versioning system and semi-automated data validators on one side meet the user demands for the simplicity and minimalism on the other side. Embodying a simple shell script in an interactive graphic user interface, we augment the efficacy of the data versioning and the integration of Java-based quality control and validation tools.</abstract>
<identifier type="citekey">riaposov-etal-2022-bringing</identifier>
<location>
<url>https://aclanthology.org/2022.eurali-1.6</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>36</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bringing Together Version Control and Quality Assurance of Language Data with LAMA
%A Riaposov, Aleksandr
%A Lazarenko, Elena
%A Lehmberg, Timm
%Y Ojha, Atul Kr.
%Y Ahmadi, Sina
%Y Liu, Chao-Hong
%Y McCrae, John P.
%S Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F riaposov-etal-2022-bringing
%X This contribution reports on work in process on project specific software and digital infrastructure components used along with corpus curation workflows in the the framework of the long-term language documentation project INEL. By bringing together scientists with different levels of technical affinity in a highly interdisciplinary working environment, the project is confronted with numerous workflow related issues. Many of them result from collaborative (remote-)work on digital corpora, which, among other things, include annotation, glossing but also quality- and consistency control. In this context several steps were taken to bridge the gap between usability and the requirements of complex data curation workflows. Components of the latter such as a versioning system and semi-automated data validators on one side meet the user demands for the simplicity and minimalism on the other side. Embodying a simple shell script in an interactive graphic user interface, we augment the efficacy of the data versioning and the integration of Java-based quality control and validation tools.
%U https://aclanthology.org/2022.eurali-1.6
%P 36-41
Markdown (Informal)
[Bringing Together Version Control and Quality Assurance of Language Data with LAMA](https://aclanthology.org/2022.eurali-1.6) (Riaposov et al., EURALI 2022)
ACL
- Aleksandr Riaposov, Elena Lazarenko, and Timm Lehmberg. 2022. Bringing Together Version Control and Quality Assurance of Language Data with LAMA. In Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, pages 36–41, Marseille, France. European Language Resources Association.