@inproceedings{riaposov-lazarenko-2024-corpus,
title = "Corpus Services: A Framework to Curate {XML} Corpus Data",
author = "Riaposov, Aleksandr and
Lazarenko, Elena",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.358/",
pages = "4030--4035",
abstract = "This paper provides a comprehensive description of the Corpus Services framework{---}a collection of Java validation tools for language corpora compiled in XML-based data formats, in particular those using EXMARaLDA corpus software. Having successfully found application in several research projects, the core functionality of the framework is currently integrated in the automated curation and publication workflows for EXMARaLDA-driven corpora of Northern Eurasian languages, as developed by the long-term project INEL. Preliminary stages of development and examples of practical use cases are covered, a structured explanation of the framework`s current functionality and operational mechanisms is provided. Furthermore, the utilization of Corpus Services is extensively illustrated within the context of INEL workflows."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riaposov-lazarenko-2024-corpus">
<titleInfo>
<title>Corpus Services: A Framework to Curate XML Corpus Data</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>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper provides a comprehensive description of the Corpus Services framework—a collection of Java validation tools for language corpora compiled in XML-based data formats, in particular those using EXMARaLDA corpus software. Having successfully found application in several research projects, the core functionality of the framework is currently integrated in the automated curation and publication workflows for EXMARaLDA-driven corpora of Northern Eurasian languages, as developed by the long-term project INEL. Preliminary stages of development and examples of practical use cases are covered, a structured explanation of the framework‘s current functionality and operational mechanisms is provided. Furthermore, the utilization of Corpus Services is extensively illustrated within the context of INEL workflows.</abstract>
<identifier type="citekey">riaposov-lazarenko-2024-corpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.358/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4030</start>
<end>4035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Services: A Framework to Curate XML Corpus Data
%A Riaposov, Aleksandr
%A Lazarenko, Elena
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F riaposov-lazarenko-2024-corpus
%X This paper provides a comprehensive description of the Corpus Services framework—a collection of Java validation tools for language corpora compiled in XML-based data formats, in particular those using EXMARaLDA corpus software. Having successfully found application in several research projects, the core functionality of the framework is currently integrated in the automated curation and publication workflows for EXMARaLDA-driven corpora of Northern Eurasian languages, as developed by the long-term project INEL. Preliminary stages of development and examples of practical use cases are covered, a structured explanation of the framework‘s current functionality and operational mechanisms is provided. Furthermore, the utilization of Corpus Services is extensively illustrated within the context of INEL workflows.
%U https://aclanthology.org/2024.lrec-main.358/
%P 4030-4035
Markdown (Informal)
[Corpus Services: A Framework to Curate XML Corpus Data](https://aclanthology.org/2024.lrec-main.358/) (Riaposov & Lazarenko, LREC-COLING 2024)
ACL
- Aleksandr Riaposov and Elena Lazarenko. 2024. Corpus Services: A Framework to Curate XML Corpus Data. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4030–4035, Torino, Italia. ELRA and ICCL.