@inproceedings{li-etal-2024-blocks,
title = "Blocks Architecture ({B}lo{A}rk): Efficient, Cost-Effective, and Incremental Dataset Architecture for {W}ikipedia Revision History",
author = "Li, Lingxi and
Yao, Zonghai and
Kwon, Sunjae and
Yu, Hong",
editor = "Lucie-Aim{\'e}e, Lucie and
Fan, Angela and
Gwadabe, Tajuddeen and
Johnson, Isaac and
Petroni, Fabio and
van Strien, Daniel",
booktitle = "Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wikinlp-1.16",
pages = "102--111",
abstract = "Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications. Wikipedia Revision History (WikiRevHist) shows the order in which edits were made to any Wiki page since its first modification. While the most up-to-date Wiki has been widely used as a training source, WikiRevHist can also be valuable resources for NLP applications. However, there are insufficient tools available to process WikiRevHist without having substantial computing resources, making additional customization, and spending extra time adapting others{'} works. Therefore, we report Blocks Architecture (BloArk), an efficiency-focused data processing architecture that reduces running time, computing resource requirements, and repeated works in processing WikiRevHist dataset. BloArk consists of three parts in its infrastructure: blocks, segments, and warehouses. On top of that, we build the core data processing pipeline: builder and modifier. The BloArk builder transforms the original WikiRevHist dataset from XML syntax into JSON Lines (JSONL) format for improving the concurrent and storage efficiency. The BloArk modifier takes previously-built warehouses to operate incremental modifications for improving the utilization of existing databases and reducing the cost of reusing others{'} works. In the end, BloArk can scale up easily in both processing Wikipedia Revision History and incrementally modifying existing dataset for downstream NLP use cases. The source code, documentations, and example usages are publicly available online and open-sourced under GPL-2.0 license.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-blocks">
<titleInfo>
<title>Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingxi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zonghai</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunjae</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Lucie-Aimée</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tajuddeen</namePart>
<namePart type="family">Gwadabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">van Strien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications. Wikipedia Revision History (WikiRevHist) shows the order in which edits were made to any Wiki page since its first modification. While the most up-to-date Wiki has been widely used as a training source, WikiRevHist can also be valuable resources for NLP applications. However, there are insufficient tools available to process WikiRevHist without having substantial computing resources, making additional customization, and spending extra time adapting others’ works. Therefore, we report Blocks Architecture (BloArk), an efficiency-focused data processing architecture that reduces running time, computing resource requirements, and repeated works in processing WikiRevHist dataset. BloArk consists of three parts in its infrastructure: blocks, segments, and warehouses. On top of that, we build the core data processing pipeline: builder and modifier. The BloArk builder transforms the original WikiRevHist dataset from XML syntax into JSON Lines (JSONL) format for improving the concurrent and storage efficiency. The BloArk modifier takes previously-built warehouses to operate incremental modifications for improving the utilization of existing databases and reducing the cost of reusing others’ works. In the end, BloArk can scale up easily in both processing Wikipedia Revision History and incrementally modifying existing dataset for downstream NLP use cases. The source code, documentations, and example usages are publicly available online and open-sourced under GPL-2.0 license.</abstract>
<identifier type="citekey">li-etal-2024-blocks</identifier>
<location>
<url>https://aclanthology.org/2024.wikinlp-1.16</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>102</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History
%A Li, Lingxi
%A Yao, Zonghai
%A Kwon, Sunjae
%A Yu, Hong
%Y Lucie-Aimée, Lucie
%Y Fan, Angela
%Y Gwadabe, Tajuddeen
%Y Johnson, Isaac
%Y Petroni, Fabio
%Y van Strien, Daniel
%S Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F li-etal-2024-blocks
%X Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications. Wikipedia Revision History (WikiRevHist) shows the order in which edits were made to any Wiki page since its first modification. While the most up-to-date Wiki has been widely used as a training source, WikiRevHist can also be valuable resources for NLP applications. However, there are insufficient tools available to process WikiRevHist without having substantial computing resources, making additional customization, and spending extra time adapting others’ works. Therefore, we report Blocks Architecture (BloArk), an efficiency-focused data processing architecture that reduces running time, computing resource requirements, and repeated works in processing WikiRevHist dataset. BloArk consists of three parts in its infrastructure: blocks, segments, and warehouses. On top of that, we build the core data processing pipeline: builder and modifier. The BloArk builder transforms the original WikiRevHist dataset from XML syntax into JSON Lines (JSONL) format for improving the concurrent and storage efficiency. The BloArk modifier takes previously-built warehouses to operate incremental modifications for improving the utilization of existing databases and reducing the cost of reusing others’ works. In the end, BloArk can scale up easily in both processing Wikipedia Revision History and incrementally modifying existing dataset for downstream NLP use cases. The source code, documentations, and example usages are publicly available online and open-sourced under GPL-2.0 license.
%U https://aclanthology.org/2024.wikinlp-1.16
%P 102-111
Markdown (Informal)
[Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History](https://aclanthology.org/2024.wikinlp-1.16) (Li et al., WikiNLP 2024)
ACL